EP4792295A1 - Explicit predictive coding for point cloud compression - Google Patents

Abstract

Some embodiments of a method may include: obtaining a previously decoded point cloud frame as a reference point cloud frame; obtaining a motion feature that describes a motion between the reference point cloud frame and a current point cloud frame; determining a predictor feature map based on the reference point cloud frame and the motion feature; obtaining a current feature map that represents the current point cloud frame given the predictor feature map as a condition; and reconstructing the current point cloud frame based on the current feature map and using the predictor feature map as a condition.

Description

EXPLICIT PREDICTIVE CODING FOR POINT CLOUD COMPRESSION

CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] The present application claims benefit of U.S. Provisional Patent Application No. 63/543,479, entitled “EXPLICIT PREDICTIVE CODING FOR POINT CLOUD COMPRESSION” and filed October 10, 2023, which is hereby incorporated by reference in its entirety.

INCORPORATION BY REFERENCE

[0002] The present application incorporates by reference in its entirety U.S. Provisional Patent Application Serial No. 63/543,484, entitled “IMPLICIT PREDICTIVE CODING FOR POINT CLOUD COMPRESSION” and filed October 10, 2023; U.S. Provisional Patent Application Serial No. 63/460,798, entitled “Generative-based

Predictive Coding for Point Cloud Compression” and filed April 20, 2023 (“798 application”); U.S. Provisional

Patent Application Serial No. 63/526,130, entitled “Generative-based Predictive Coding for LiDAR Point Cloud

Compression” and filed July 11 , 2023 (“‘130 application”); U.S. Provisional Patent Application Serial No. 63/388,600, entitled “Deep Distribution-Aware Point Feature Extractor for Al-Based Point Cloud Compression” and filed July 12, 2022 ('“600 application”); U.S. Provisional Patent Application Serial

No. 63/438,212, entitled “Context-Aware Voxel-Based Upsampling for Point Cloud Processing” and filed January 10, 2023 (‘“212 application”); and International Patent Application Serial No. 63/424,421 , entitled “Heterogeneous Mesh Autoencoders” and filed November 10, 2022 (“‘421 application”).

BACKGROUND

[0003] Point cloud is a data format used across several business domains from autonomous driving, robotics, AR/VR, civil engineering, computer graphics, to the animation /movie industry. 3D LiDAR sensors have been deployed in self-driving cars, and affordable LiDAR sensors are released from, e g., Velodyne Velabit, Apple iPad Pro 2020, and Intel RealSense LiDAR camera L515. With advances in sensing technologies, 3D point cloud data becomes more practical than ever and is expected to be an ultimate enabler in the applications mentioned. [0004] Point cloud data is also believed to consume a large portion of network traffic, e.g., immersive communications (VR/AR) and cars connected over a 5G network. Efficient representation formats may be used with point clouds and communication. In particular, raw point cloud data is organized and processed for the purposes of world modeling & sensing. Compression of raw point clouds may be used with storage and transmission of data in related scenarios.

SUMMARY

[0005] A first example method in accordance with some embodiments may include: obtaining a previously decoded point cloud frame as a reference point cloud frame; obtaining a motion feature that describes a motion between the reference point cloud frame and a current point cloud frame; determining a predictor feature map based on the reference point cloud frame and the motion feature; obtaining a current feature map that represents the current point cloud frame given the predictor feature map as a condition; and reconstructing the current point cloud frame based on the current feature map and using the predictor feature map as a condition.

[0006] For some embodiments of the first example method, obtaining the motion feature that describes motion between the reference point cloud frame and the current point cloud frame includes: performing motion analysis to generate a motion feature map using the reference point cloud frame and the current point cloud frame as inputs; and entropy encoding the motion feature map to generate the motion feature.

[0007] For some embodiments of the first example method, obtaining the motion feature that describes motion between the reference point cloud frame and the current point cloud frame includes: performing a feature extraction on the reference point cloud frame to generate a first feature map; performing a feature extraction on the current point cloud frame to generate a second feature map; fusing the first and second feature maps to generate a fused feature map; and performing a feature aggregation on the fused feature map to generate the motion feature.

[0008] For some embodiments of the first example method, the reference point cloud frame and the current point cloud frame are voxel-based representations, and performing the feature extraction on the reference point cloud frame includes: passing the reference point cloud frame through one or more multi-layer perceptron (MLP) blocks; and passing an output of the one or more MLP blocks through one or more convolutional layers to generate the first feature map, and performing the feature extraction on the current point cloud frame includes: passing the current point cloud frame through one or more multi-layer perceptron (MLP) blocks; and passing an output of the one or more MLP blocks through one or more convolutional layers to generate the second feature map.

[0009] For some embodiments of the first example method, the reference point cloud frame and the current point cloud frame are point-based representations, and performing the feature extraction on the reference point cloud frame includes: performing a block partition on the reference point cloud frame; and performing a blockwise feature extraction on the block partitioned reference point cloud frame to generate the first feature map, and performing the feature extraction on the current point cloud frame includes: performing a block partition on the current point cloud frame; and performing a blockwise feature extraction on the block partitioned current point cloud frame to generate the second feature map.

[0010] For some embodiments of the first example method, obtaining the motion feature includes performing motion analysis training.

[0011] For some embodiments of the first example method, determining the predictor feature map based on the reference point cloud frame and the motion feature includes: performing a feature extraction on the reference point cloud frame to generate a first feature map; concatenating the first feature map with the motion feature; passing the concatenated first feature map through one or more multi-layer perceptron (MLP) blocks; and passing an output of the one or more MLP blocks through one or more convolutional layers to generate the predictor feature map.

[0012] For some embodiments of the first example method, wherein performing the feature extraction on the reference point cloud frame includes performing a point synthesis.

[0013] For some embodiments of the first example method, wherein performing the feature extraction on the current point cloud frame includes performing a point synthesis.

[0014] A first example apparatus in accordance with some embodiments may include: a processor; and a non-transitory computer-readable medium storing instructions operative, when executed by the processor, to cause the apparatus to perform any one of the methods listed above.

[0015] A second example method in accordance with some embodiments may include: obtaining a previously encoded point cloud frame as a reference point cloud frame; obtaining a motion feature that describes motion between the reference point cloud frame and a current point cloud frame; determining a predictor feature map based on the reference point cloud frame and the motion feature; determining a current feature map that represents the current point cloud frame given the predictor feature map as a condition; and encoding the current feature map into a bitstream using the predictor feature map as a condition.

[0016] For some embodiments of the second example method, obtaining the motion feature that describes motion between the reference point cloud frame and the current point cloud frame includes: performing motion analysis to generate a motion feature map using the reference point cloud frame and the current point cloud frame as inputs; and entropy encoding the motion feature map to generate the motion feature.

[0017] For some embodiments of the second example method, obtaining the motion feature that describes motion between the reference point cloud frame and the current point cloud frame includes: performing a feature extraction on the reference point cloud frame to generate a first feature map; performing a feature extraction on the current point cloud frame to generate a second feature map; fusing the first and second feature maps to generate a fused feature map; and performing a feature aggregation on the fused feature map to generate the motion feature.

[0018] For some embodiments of the second example method, the reference point cloud frame and the current point cloud frame are voxel-based representations, and performing the feature extraction on the reference point cloud frame includes: passing the reference point cloud frame through one or more multi-layer perceptron (MLP) blocks; and passing an output of the one or more MLP blocks through one or more convolutional layers to generate the first feature map, and performing the feature extraction on the current point cloud frame includes: passing the current point cloud frame through one or more multi-layer perceptron (MLP) blocks; and passing an output of the one or more MLP blocks through one or more convolutional layers to generate the second feature map.

[0019] For some embodiments of the second example method, the reference point cloud frame and the current point cloud frame are point-based representations, and performing the feature extraction on the reference point cloud frame includes: performing a block partition on the reference point cloud frame; and performing a blockwise feature extraction on the block partitioned reference point cloud frame to generate the first feature map, and performing the feature extraction on the current point cloud frame includes: performing a block partition on the current point cloud frame; and performing a blockwise feature extraction on the block partitioned current point cloud frame to generate the second feature map.

[0020] For some embodiments of the second example method, obtaining the motion feature includes performing motion analysis training. [0021] For some embodiments of the second example method, determining the predictor feature map based on the reference point cloud frame and the motion feature includes: performing a feature extraction on the reference point cloud frame to generate a first feature map; concatenating the first feature map with the motion feature; passing the concatenated first feature map through one or more multi-layer perceptron (MLP) blocks; and passing an output of the one or more MLP blocks through one or more convolutional layers to generate the predictor feature map.

[0022] For some embodiments of the second example method, determining the current feature map includes: performing a feature extraction on the current point cloud frame to generate a second feature map; concatenating the second feature map with the predictor feature map; passing the concatenated second feature map through one or more multi-layer perceptron (MLP) blocks; and passing an output of the one or more MLP blocks through one or more convolutional layers to generate the current feature map.

[0023] For some embodiments of the second example method, performing the feature extraction on at least one of the reference point cloud frame and the current point cloud frame includes using an Inception-ResNet block.

[0024] A second example apparatus in accordance with some embodiments may include: a processor; and a non-transitory computer-readable medium storing instructions operative, when executed by the processor, to cause the apparatus to perform any one of the methods listed above.

[0025] A third example apparatus in accordance with some embodiments may include at least one processor configured to perform any one of the methods listed above.

[0026] A fourth example apparatus in accordance with some embodiments may include a computer-readable medium storing instructions for causing one or more processors to perform any one of the methods listed above.

[0027] A fifth example apparatus in accordance with some embodiments may include: at least one processor and at least one non-transitory computer-readable medium storing instructions for causing the at least one processor to perform any one of the methods listed above.

[0028] An example signal in accordance with some embodiments may include a bitstream generated according to any one of the methods listed above.

BRIEF DESCRIPTION OF THE DRAWINGS [0029] FIG. 1A is a system diagram illustrating an example communications system according to some embodiments.

[0030] FIG. 1 B is a system diagram illustrating an example wireless transmit/receive unit (WTRU) that may be used within the communications system illustrated in FIG. 1 A according to some embodiments.

[0031] FIG. 1 C is a system diagram illustrating an example set of interfaces for a system according to some embodiments.

[0032] FIG. 2A is a functional block diagram of block-based video encoder, such as an encoder used for Versatile Video Coding (WC), according to some embodiments.

[0033] FIG. 2B is a functional block diagram of a block-based video decoder, such as a decoder used for WC, according to some embodiments.

[0034] FIG. 3A is a schematic side view illustrating an example waveguide display that may be used with extended reality (XR) applications according to some embodiments.

[0035] FIG. 3B is a schematic side view illustrating an example alternative display type that may be used with extended reality applications according to some embodiments.

[0036] FIG. 3C is a schematic side view illustrating an example alternative display type that may be used with extended reality applications according to some embodiments.

[0037] FIG. 4 is a process diagram illustrating an example codec encoding and decoding process with explicit prediction according to some embodiments.

[0038] FIG. 5 is a process diagram illustrating an example training process for the motion analysis according to some embodiments.

[0039] FIG. 6 is a process diagram illustrating an example training process for a predictor feature generation block according to some embodiments.

[0040] FIG. 7 is a process diagram illustrating an example motion analysis process according to some embodiments.

[0041] FIG. 8 is a process diagram illustrating an example feature extraction for voxel-based representation according to some embodiments. [0042] FIG. 9 is a process diagram illustrating an example feature extraction for point-based representation according to some embodiments.

[0043] FIG. 10 is a process diagram illustrating an example feature aggregation (FC block) according to some embodiments.

[0044] FIG. 11 is a process diagram illustrating an example feature predictor generation (FA block) according to some embodiments.

[0045] FIG. 12 is a process diagram illustrating an example feature aggregation/extraction in the encoder (FE block) according to some embodiments.

[0046] FIG. 13 is a process diagram illustrating an example feature aggregation/extraction in the decoder (FD block) according to some embodiments.

[0047] FIG. 14 is a process diagram illustrating an example feature aggregation/extraction in the decoder (FD block) according to some embodiments.

[0048] FIG. 15 is a process diagram illustrating an example conditional feature decoder according to some embodiments.

[0049] FIG. 16 is a process diagram illustrating an example point synthesis block (PS block) according to some embodiments.

[0050] FIG. 17 is a process diagram illustrating an example Inception-ResNet block for feature aggregation according to some embodiments.

[0051] FIG. 18 is a process diagram illustrating an example transformer block for feature aggregation according to some embodiments.

[0052] FIG. 19 is a process diagram illustrating an example self-attention block according to some embodiments.

[0053] FIG. 20 is a flowchart illustrating an example decoding process according to some embodiments.

[0054] FIG. 21 is a flowchart illustrating an example encoding process according to some embodiments.

[0055] The entities, connections, arrangements, and the like that are depicted in— and described in connection with— the various figures are presented by way of example and not byway of limitation. As such, any and all statements or other indications as to what a particular figure “depicts,” what a particular element or entity in a particular figure “is” or “has,” and any and all similar statements— that may in isolation and out of context be read as absolute and therefore limiting— may only properly be read as being constructively preceded by a clause such as “In at least one embodiment, ... " For brevity and clarity of presentation, this implied leading clause is not repeated ad nauseum in the detailed description.

DETAILED DESCRIPTION

[0056] FIG. 1A is a diagram illustrating an example communications system 100 in which one or more disclosed embodiments may be implemented. The communications system 100 may be a multiple access system that provides content, such as voice, data, video, messaging, broadcast, etc., to multiple wireless users. The communications system 100 may enable multiple wireless users to access such content through the sharing of system resources, including wireless bandwidth. For example, the communications systems 100 may employ one or more channel access methods, such as code division multiple access (CDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal FDMA (OFDMA), single-carrier FDMA (SC-FDMA), zero-tail unique-word DFT-Spread OFDM (ZT UW DTS-s OFDM), unique word OFDM (UW-OFDM), resource block-filtered OFDM, filter bank multicarrier (FBMC), and the like.

[0057] As shown in FIG. 1A, the communications system 100 may include wireless transmit/receive units (WTRUs) 102a, 102b, 102c, 102d, a RAN 104/113, a ON 106, a public switched telephone network (PSTN) 108, the Internet 110, and other networks 112, though it will be appreciated that the disclosed embodiments contemplate any number of WTRUs, base stations, networks, and/or network elements. Each of the WTRUs 102a, 102b, 102c, 102d may be any type of device configured to operate and/or communicate in a wireless environment. By way of example, the WTRUs 102a, 102b, 102c, 102d, any of which may be referred to as a “station” and/or a “STA”, may be configured to transmit and/or receive wireless signals and may include a user equipment (UE), a mobile station, a fixed or mobile subscriber unit, a subscription-based unit, a pager, a cellular telephone, a personal digital assistant (PDA), a smartphone, a laptop, a netbook, a personal computer, a wireless sensor, a hotspot or Mi-Fi device, an Internet of Things (loT) device, a watch or other wearable, a head-mounted display (HMD), a vehicle, a drone, a medical device and applications (e.g. , remote surgery), an industrial device and applications (e.g., a robot and/or other wireless devices operating in an industrial and/or an automated processing chain contexts), a consumer electronics device, a device operating on commercial and/or industrial wireless networks, and the like. Any of the WTRUs 102a, 102b, 102c and 102d may be interchangeably referred to as a UE. [0058] The communications systems 100 may also include a base station 114a and/or a base station 114b. Each of the base stations 114a, 114b may be any type of device configured to wirelessly interface with at least one of the WTRUs 102a, 102b, 102c, 102d to facilitate access to one or more communication networks, such as the CN 106, the Internet 110, and/or the other networks 112. By way of example, the base stations 114a, 114b may be a base transceiver station (BTS), a Node-B, an eNode B, a Home Node B, a Home eNode B, a gNB, a NR NodeB, a site controller, an access point (AP), a wireless router, and the like. While the base stations 114a, 114b are each depicted as a single element, it will be appreciated that the base stations 114a, 114b may include any number of interconnected base stations and/or network elements.

[0059] The base station 114a may be part of the RAN 104/113, which may also include other base stations and/or network elements (not shown), such as a base station controller (BSC), a radio network controller (RNC), relay nodes, etc. The base station 114a and/or the base station 114b may be configured to transmit and/or receive wireless signals on one or more carrier frequencies, which may be referred to as a cell (not shown). These frequencies may be in licensed spectrum, unlicensed spectrum, or a combination of licensed and unlicensed spectrum. A cell may provide coverage for a wireless service to a specific geographical area that may be relatively fixed or that may change over time. The cell may further be divided into cell sectors. For example, the cell associated with the base station 114a may be divided into three sectors. Thus, in one embodiment, the base station 114a may include three transceivers, i.e., one for each sector of the cell. In an embodiment, the base station 114a may employ multiple-input multiple output (MIMO) technology and may utilize multiple transceivers for each sector of the cell. For example, beamforming may be used to transmit and/or receive signals in desired spatial directions.

[0060] The base stations 114a, 114b may communicate with one or more of the WTRUs 102a, 102b, 102c, 102d over an air interface 116, which may be any suitable wireless communication link (e.g., radio frequency (RF), microwave, centimeter wave, micrometer wave, infrared (IR), ultraviolet (UV), visible light, etc.). The air interface 116 may be established using any suitable radio access technology (RAT).

[0061] More specifically, as noted above, the communications system 100 may be a multiple access system and may employ one or more channel access schemes, such as CDMA, TDMA, FDMA, OFDMA, SC-FDMA, and the like. For example, the base station 114a in the RAN 104/113 and the WTRUs 102a, 102b, 102c may implement a radio technology such as Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access (UTRA), which may establish the air interface 116 using wideband CDMA (WCDMA). WCDMA may include communication protocols such as High-Speed Packet Access (HSPA) and/or Evolved HSPA (HSPA+). HSPA may include High-Speed Downlink (DL) Packet Access (HSDPA) and/or High-Speed UL Packet Access (HSUPA).

[0062] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as Evolved UMTS Terrestrial Radio Access (E-UTRA), which may establish the air interface 116 using Long Term Evolution (LTE) and/or LTE-Advanced (LTE-A) and/or LTE-Advanced Pro (LTE-A Pro).

[0063] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as NR Radio Access , which may establish the air interface 116 using New Radio (NR).

[0064] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement multiple radio access technologies. For example, the base station 114a and the WTRUs 102a, 102b, 102c may implement LTE radio access and NR radio access together, for instance using dual connectivity (DC) principles. Thus, the air interface utilized by WTRUs 102a, 102b, 102c may be characterized by multiple types of radio access technologies and/or transmissions sent to/from multiple types of base stations (e.g., a eNB and a gNB).

[0065] In other embodiments, the base station 114a and the WTRUs 102a, 102b, 102c may implement radio technologies such as IEEE 802.11 (i.e., Wireless Fidelity (WiFi), IEEE 802.16 (i.e., Worldwide Interoperability for Microwave Access (WiMAX)), CDMA2000, CDMA2000 1X, CDMA2000 EV-DO, Interim Standard 2000 (IS- 2000), Interim Standard 95 (IS-95), Interim Standard 856 (IS-856), Global System for Mobile communications (GSM), Enhanced Data rates for GSM Evolution (EDGE), GSM EDGE (GERAN), and the like.

[0066] The base station 114b in FIG. 1A may be a wireless router, Home Node B, Home eNode B, or access point, for example, and may utilize any suitable RAT for facilitating wireless connectivity in a localized area, such as a place of business, a home, a vehicle, a campus, an industrial facility, an air corridor (e.g., for use by drones), a roadway, and the like. In one embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.11 to establish a wireless local area network (WLAN). In an embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.15 to establish a wireless personal area network (WPAN). In yet another embodiment, the base station 114b and the WTRUs 102c, 102d may utilize a cellular-based RAT (e.g., WCDMA, CDMA2000, GSM, LTE, LTE-A, LTE-A Pro, NR etc.) to establish a picocell or femtocell. As shown in FIG. 1 A, the base station 114b may have a direct connection to the Internet 110. Thus, the base station 114b may not be required to access the Internet 110 via the CN 106. [0067] The RAN 104/113 may be in communication with the CN 106, which may be any type of network configured to provide voice, data, applications, and/or voice over internet protocol (VoIP) services to one or more of the WTRUs 102a, 102b, 102c, 102d. The data may have varying quality of service (QoS) requirements, such as differing throughput requirements, latency requirements, error tolerance requirements, reliability requirements, data throughput requirements, mobility requirements, and the like. The CN 106 may provide call control, billing services, mobile location-based services, pre-paid calling, Internet connectivity, video distribution, etc., and/or perform high-level security functions, such as user authentication. Although not shown in FIG. 1A, it will be appreciated that the RAN 104/113 and/or the CN 106 may be in direct or indirect communication with other RANs that employ the same RAT as the RAN 104/113 or a different RAT. For example, in addition to being connected to the RAN 104/113, which may be utilizing a NR radio technology, the CN 106 may also be in communication with another RAN (not shown) employing a GSM, UMTS, CDMA 2000, WiMAX, E-UTRA, or WiFi radio technology.

[0068] The CN 106 may also serve as a gateway for the WTRUs 102a, 102b, 102c, 102d to access the PSTN 108, the Internet 110, and/or the other networks 112. The PSTN 108 may include circuit-switched telephone networks that provide plain old telephone service (POTS). The Internet 110 may include a global system of interconnected computer networks and devices that use common communication protocols, such as the transmission control protocol (TCP), user datagram protocol (UDP) and/or the internet protocol (IP) in the TCP/IP internet protocol suite. The networks 112 may include wired and/or wireless communications networks owned and/or operated by other service providers. For example, the networks 112 may include another CN connected to one or more RANs, which may employ the same RAT as the RAN 104/113 or a different RAT.

[0069] Some or all of the WTRUs 102a, 102b, 102c, 102d in the communications system 100 may include multi-mode capabilities (e.g., the WTRUs 102a, 102b, 102c, 102d may include multiple transceivers for communicating with different wireless networks over different wireless links). For example, the WTRU 102c shown in FIG. 1A may be configured to communicate with the base station 114a, which may employ a cellularbased radio technology, and with the base station 114b, which may employ an IEEE 802 radio technology.

[0070] FIG. 1B is a system diagram illustrating an example WTRU 102. As shown in FIG. 1 B, the WTRU 102 may include a processor 118, a transceiver 120, a transmit/receive element 122, a speaker/microphone 124, a keypad 126, a display/touchpad 128, non-removable memory 130, removable memory 132, a power source 134, a global positioning system (GPS) chipset 136, and/or other peripherals 138, among others. It will be appreciated that the WTRU 102 may include any sub-combination of the foregoing elements while remaining consistent with an embodiment.

[0071] The processor 118 may be a general purpose processor, a special purpose processor, a conventional processor, a digital signal processor (DSP), a plurality of microprocessors, one or more microprocessors in association with a DSP core, a controller, a microcontroller, Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) circuits, any other type of integrated circuit (IC), a state machine, and the like. The processor 118 may perform signal coding, data processing, power control, input/output processing, and/or any other functionality that enables the WTRU 102 to operate in a wireless environment. The processor 118 may be coupled to the transceiver 120, which may be coupled to the transmit/receive element 122. While FIG. 1 B depicts the processor 118 and the transceiver 120 as separate components, it will be appreciated that the processor 118 and the transceiver 120 may be integrated together in an electronic package or chip.

[0072] The transmit/receive element 122 may be configured to transmit signals to, or receive signals from, a base station (e.g., the base station 114a) over the air interface 116. For example, in one embodiment, the transmit/receive element 122 may be an antenna configured to transmit and/or receive RF signals. In an embodiment, the transmit/receive element 122 may be an emitter/detector configured to transmit and/or receive IR, UV, or visible light signals, for example. In yet another embodiment, the transmit/receive element 122 may be configured to transmit and/or receive both RF and light signals. It will be appreciated that the transmit/receive element 122 may be configured to transmit and/or receive any combination of wireless signals.

[0073] Although the transmit/receive element 122 is depicted in FIG. 1 B as a single element, the WTRU 102 may include any number of transmit/receive elements 122. More specifically, the WTRU 102 may employ MIMO technology. Thus, in one embodiment, the WTRU 102 may include two or more transmit/receive elements 122 (e.g., multiple antennas) for transmitting and receiving wireless signals over the air interface 116.

[0074] The transceiver 120 may be configured to modulate the signals that are to be transmitted by the transmit/receive element 122 and to demodulate the signals that are received by the transmit/receive element 122. As noted above, the WTRU 102 may have multi-mode capabilities. Thus, the transceiver 120 may include multiple transceivers for enabling the WTRU 102 to communicate via multiple RATs, such as NR and IEEE 802.11, for example.

[0075] The processor 118 of the WTRU 102 may be coupled to, and may receive user input data from, the speaker/microphone 124, the keypad 126, and/or the display/touchpad 128 (e.g., a liquid crystal display (LCD) display unit or organic light-emitting diode (OLED) display unit). The processor 118 may also output user data to the speaker/microphone 124, the keypad 126, and/or the display/touchpad 128. In addition, the processor 118 may access information from, and store data in, any type of suitable memory, such as the non-removable memory 130 and/or the removable memory 132. The non-removable memory 130 may include random-access memory (RAM), read-only memory (ROM), a hard disk, or any other type of memory storage device. The removable memory 132 may include a subscriber identity module (SIM) card, a memory stick, a secure digital (SD) memory card, and the like. In other embodiments, the processor 118 may access information from, and store data in, memory that is not physically located on the WTRU 102, such as on a server or a home computer (not shown).

[0076] The processor 118 may receive power from the power source 134, and may be configured to distribute and/or control the power to the other components in the WTRU 102. The power source 134 may be any suitable device for powering the WTRU 102. For example, the power source 134 may include one or more dry cell batteries (e.g. , nickel-cadmium (NiCd), nickel-zinc (NiZn), nickel metal hydride (NiMH), lithium-ion (Li-ion), etc.), solar cells, fuel cells, and the like.

[0077] The processor 118 may also be coupled to the GPS chipset 136, which may be configured to provide location information (e.g., longitude and latitude) regarding the current location of the WTRU 102. In addition to, or in lieu of, the information from the GPS chipset 136, the WTRU 102 may receive location information over the air interface 116 from a base station (e.g., base stations 114a, 114b) and/or determine its location based on the timing of the signals being received from two or more nearby base stations. It will be appreciated that the WTRU 102 may acquire location information by way of any suitable location-determination method while remaining consistent with an embodiment.

[0078] The processor 118 may further be coupled to other peripherals 138, which may include one or more software and/or hardware modules that provide additional features, functionality and/or wired or wireless connectivity. For example, the peripherals 138 may include an accelerometer, an e-compass, a satellite transceiver, a digital camera (for photographs and/or video), a universal serial bus (USB) port, a vibration device, a television transceiver, a hands free headset, a Bluetooth® module, a frequency modulated (FM) radio unit, a digital music player, a media player, a video game player module, an Internet browser, a Virtual Reality and/or Augmented Reality (VR/AR) device, an activity tracker, and the like. The peripherals 138 may include one or more sensors, the sensors may be one or more of a gyroscope, an accelerometer, a hall effect sensor, a magnetometer, an orientation sensor, a proximity sensor, a temperature sensor, a time sensor; a geolocation sensor; an altimeter, a light sensor, a touch sensor, a magnetometer, a barometer, a gesture sensor, a biometric sensor, and/or a humidity sensor.

[0079] The WTRU 102 may include a full duplex radio for which transmission and reception of some or all of the signals (e.g., associated with particular subframes for both the UL (e.g., for transmission) and downlink (e.g., for reception) may be concurrent and/or simultaneous. The full duplex radio may include an interference management unit to reduce and or substantially eliminate self-interference via either hardware (e.g., a choke) or signal processing via a processor (e.g., a separate processor (not shown) or via processor 118). In an embodiment, the WTRU 102 may include a half-duplex radio for which transmission and reception of some or all of the signals (e.g., associated with particular subframes for either the UL (e.g., for transmission) or the downlink (e.g., for reception)).

[0080] Although the WTRU is described in FIGs. 1 A-1 B as a wireless terminal, it is contemplated that in certain representative embodiments that such a terminal may use (e.g., temporarily or permanently) wired communication interfaces with the communication network.

[0081] In representative embodiments, the other network 112 may be a WLAN.

[0082] In view of FIGs. 1 A-1 B, and the corresponding description, one or more, or all, of the functions described herein may be performed by one or more emulation devices (not shown). The emulation devices may be one or more devices configured to emulate one or more, or all, of the functions described herein. For example, the emulation devices may be used to test other devices and/or to simulate network and/or WTRU functions.

[0083] The emulation devices may be designed to implement one or more tests of other devices in a lab environment and/or in an operator network environment. For example, the one or more emulation devices may perform the one or more, or all, functions while being fully or partially implemented and/or deployed as part of a wired and/or wireless communication network in order to test other devices within the communication network. The one or more emulation devices may perform the one or more, or all, functions while being temporarily implemented/deployed as part of a wired and/or wireless communication network. The emulation device may be directly coupled to another device for purposes of testing and/or may performing testing using over-the-air wireless communications.

[0084] The one or more emulation devices may perform the one or more, including all, functions while not being implemented/deployed as part of a wired and/or wireless communication network. For example, the emulation devices may be utilized in a testing scenario in a testing laboratory and/or a non-deployed (e.g., testing) wired and/or wireless communication network in order to implement testing of one or more components. The one or more emulation devices may be test equipment. Direct RF coupling and/or wireless communications via RF circuitry (e.g., which may include one or more antennas) may be used by the emulation devices to transmit and/or receive data.

[0085] FIG. 1 C is a system diagram illustrating an example set of interfaces for a system according to some embodiments. An extended reality display device, together with its control electronics, may be implemented for some embodiments. System 150 can be embodied as a device including the various components described below and is configured to perform one or more of the aspects described in this document. Examples of such devices, include, but are not limited to, various electronic devices such as personal computers, laptop computers, smartphones, tablet computers, digital multimedia set top boxes, digital television receivers, personal video recording systems, connected home appliances, and servers. Elements of system 150, singly or in combination, can be embodied in a single integrated circuit (IC), multiple ICs, and/or discrete components. For example, in at least one embodiment, the processing and encoder/decoder elements of system 150 are distributed across multiple ICs and/or discrete components. In various embodiments, the system 150 is communicatively coupled to one or more other systems, or other electronic devices, via, for example, a communications bus or through dedicated input and/or output ports. In various embodiments, the system 150 is configured to implement one or more of the aspects described in this document.

[0086] The system 150 includes at least one processor 152 configured to execute instructions loaded therein for implementing, for example, the various aspects described in this document. Processor 152 may include embedded memory, input output interface, and various other circuitries as known in the art. The system 150 includes at least one memory 154 (e.g., a volatile memory device, and/or a non-volatile memory device). System 150 may include a storage device 158, which can include non-volatile memory and/or volatile memory, including, but not limited to, Electrically Erasable Programmable Read-Only Memory (EEPROM), Read-Only Memory (ROM), Programmable Read-Only Memory (PROM), Random Access Memory (RAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), flash, magnetic disk drive, and/or optical disk drive. The storage device 158 can include an internal storage device, an attached storage device (including detachable and non-detachable storage devices), and/or a network accessible storage device, as non-limiting examples.

[0087] System 150 includes an encoder/decoder module 156 configured, for example, to process data to provide an encoded video or decoded video, and the encoder/decoder module 156 can include its own processor and memory. The encoder/decoder module 156 represents module(s) that can be included in a device to perform the encoding and/or decoding functions. As is known, a device can include one or both of the encoding and decoding modules. Additionally, encoder/decoder module 156 can be implemented as a separate element of system 150 or can be incorporated within processor 152 as a combination of hardware and software as known to those skilled in the art.

[0088] Program code to be loaded onto processor 152 or encoder/decoder 156 to perform the various aspects described in this document can be stored in storage device 158 and subsequently loaded onto memory 154 for execution by processor 152. In accordance with various embodiments, one or more of processor 152, memory 154, storage device 158, and encoder/decoder module 156 can store one or more of various items during the performance of the processes described in this document. Such stored items can include, but are not limited to, the input video, the decoded video or portions of the decoded video, the bitstream, matrices, variables, and intermediate or final results from the processing of equations, formulas, operations, and operational logic.

[0089] In some embodiments, memory inside of the processor 152 and/or the encoder/decoder module 156 is used to store instructions and to provide working memory for processing that is needed during encoding or decoding. In other embodiments, however, a memory external to the processing device (for example, the processing device can be either the processor 152 or the encoder/decoder module 152) is used for one or more of these functions. The external memory can be the memory 154 and/or the storage device 158, for example, a dynamic volatile memory and/or a non-volatile flash memory. In several embodiments, an external non-volatile flash memory is used to store the operating system of, for example, a television. In at least one embodiment, a fast external dynamic volatile memory such as a RAM is used as working memory for video coding and decoding operations, such as for MPEG-2 (MPEG refers to the Moving Picture Experts Group, MPEG-2 is also referred to as ISO/IEC 13818, and 13818-1 is also known as H.222, and 13818-2 is also known as H.262), HEVC (HEVC refers to High Efficiency Video Coding, also known as H.265 and MPEG-H Part 2), or WC (Versatile Video Coding, a new standard being developed by JVET, the Joint Video Experts Team).

[0090] The input to the elements of system 150 can be provided through various input devices as indicated in block 172. Such input devices include, but are not limited to, (i) a radio frequency (RF) portion that receives an RF signal transmitted, for example, over the air by a broadcaster, (ii) a Component (COMP) input terminal (or a set of COMP input terminals), (iii) a Universal Serial Bus (USB) input terminal, and/or (iv) a High Definition Multimedia Interface (HDMI) input terminal. Other examples, not shown in FIG. 1 C, include composite video. [0091] In various embodiments, the input devices of block 172 have associated respective input processing elements as known in the art. For example, the RF portion can be associated with elements suitable for (i) selecting a desired frequency (also referred to as selecting a signal, or band-limiting a signal to a band of frequencies), (ii) downconverting the selected signal, (iii) band-limiting again to a narrower band of frequencies to select (for example) a signal frequency band which can be referred to as a channel in certain embodiments, (iv) demodulating the downconverted and band-limited signal, (v) performing error correction, and (vi) demultiplexing to select the desired stream of data packets. The RF portion of various embodiments includes one or more elements to perform these functions, for example, frequency selectors, signal selectors, bandlimiters, channel selectors, filters, downconverters, demodulators, error correctors, and demultiplexers. The RF portion can include a tuner that performs various of these functions, including, for example, downconverting the received signal to a lower frequency (for example, an intermediate frequency or a near-baseband frequency) or to baseband. In one set-top box embodiment, the RF portion and its associated input processing element receives an RF signal transmitted over a wired (for example, cable) medium, and performs frequency selection by filtering, downconverting, and filtering again to a desired frequency band. Various embodiments rearrange the order of the above-described (and other) elements, remove some of these elements, and/or add other elements performing similar or different functions. Adding elements can include inserting elements in between existing elements, such as, for example, inserting amplifiers and an analog-to-digital converter. In various embodiments, the RF portion includes an antenna.

[0092] Additionally, the USB and/or HDMI terminals can include respective interface processors for connecting system 150 to other electronic devices across USB and/or HDMI connections. It is to be understood that various aspects of input processing, for example, Reed-Solomon error correction, can be implemented, for example, within a separate input processing IC or within processor 152 as necessary. Similarly, aspects of USB or HDMI interface processing can be implemented within separate interface ICs or within processor 152 as necessary. The demodulated, error corrected, and demultiplexed stream is provided to various processing elements, including, for example, processor 152, and encoder/decoder 156 operating in combination with the memory and storage elements to process the datastream as necessary for presentation on an output device.

[0093] Various elements of system 150 can be provided within an integrated housing, Within the integrated housing, the various elements can be interconnected and transmit data therebetween using suitable connection arrangement 174, for example, an internal bus as known in the art, including the I nter-IC (I2C) bus, wiring, and printed circuit boards. [0094] The system 150 includes communication interface 160 that enables communication with other devices via communication channel 162. The communication interface 160 can include, but is not limited to, a transceiver configured to transmit and to receive data over communication channel 162. The communication interface 160 can include, but is not limited to, a modem or network card and the communication channel 162 can be implemented, for example, within a wired and/or a wireless medium.

[0095] Data is streamed, or otherwise provided, to the system 150, in various embodiments, using a wireless network such as a Wi-Fi network, for example IEEE 802.11 (IEEE refers to the Institute of Electrical and Electronics Engineers). The Wi-Fi signal of these embodiments is received over the communications channel 162 and the communications interface 160 which are adapted for Wi-Fi communications. The communications channel 162 of these embodiments is typically connected to an access point or router that provides access to external networks including the Internet for allowing streaming applications and other over-the-top communications. Other embodiments provide streamed data to the system 150 using a set-top box that delivers the data over the HDMI connection of the input block 172. Still other embodiments provide streamed data to the system 150 using the RF connection of the input block 172. As indicated above, various embodiments provide data in a non-streaming manner. Additionally, various embodiments use wireless networks other than Wi-Fi, for example a cellular network or a Bluetooth network.

[0096] The system 150 can provide an output signal to various output devices, including a display 176, speakers 178, and other peripheral devices 180. The display 176 of various embodiments includes one or more of, for example, a touchscreen display, an organic light-emitting diode (OLED) display, a curved display, and/or a foldable display. The display 176 can be for a television, a tablet, a laptop, a cell phone (mobile phone), or other device. The display 176 can also be integrated with other components (for example, as in a smart phone), or separate (for example, an external monitor for a laptop). The other peripheral devices 180 include, in various examples of embodiments, one or more of a stand-alone digital video disc (or digital versatile disc) (DVR, for both terms), a disk player, a stereo system, and/or a lighting system. Various embodiments use one or more peripheral devices 180 that provide a function based on the output of the system 150. For example, a disk player performs the function of playing the output of the system 150.

[0097] In various embodiments, control signals are communicated between the system 150 and the display 176, speakers 178, or other peripheral devices 180 using signaling such as AV.Link, Consumer Electronics Control (CEC), or other communications protocols that enable device-to-device control with or without user intervention. The output devices can be communicatively coupled to system 150 via dedicated connections through respective interfaces 164, 166, and 168. Alternatively, the output devices can be connected to system 150 using the communications channel 162 via the communications interface 160. The display 176 and speakers 178 can be integrated in a single unit with the other components of system 150 in an electronic device such as, for example, a television. In various embodiments, the display interface 164 includes a display driver, such as, for example, a timing controller (T Con) chip.

[0098] The display 176 and speaker 178 can alternatively be separate from one or more of the other components, for example, if the RF portion of input 172 is part of a separate set-top box. In various embodiments in which the display 176 and speakers 178 are external components, the output signal can be provided via dedicated output connections, including, for example, HDMI ports, USB ports, or COMP outputs.

[0099] The system 150 may include one or more sensor devices 168. Examples of sensor devices that may be used include one or more GPS sensors, gyroscopic sensors, accelerometers, light sensors, cameras, depth cameras, microphones, and/or magnetometers. Such sensors may be used to determine information such as user’s position and orientation. Where the system 150 is used as the control module for an extended reality display (such as control modules 124, 132), the user’s position and orientation may be used in determining how to render image data such that the user perceives the correct portion of a virtual object or virtual scene from the correct point of view. In the case of head-mounted display devices, the position and orientation of the device itself may be used to determine the position and orientation of the user for the purpose of rendering virtual content. In the case of other display devices, such as a phone, a tablet, a computer monitor, or a television, other inputs may be used to determine the position and orientation of the user for the purpose of rendering content. For example, a user may select and/or adjust a desired viewpoint and/or viewing direction with the use of a touch screen, keypad or keyboard, trackball, joystick, or other input. Where the display device has sensors such as accelerometers and/or gyroscopes, the viewpoint and orientation used for the purpose of rendering content may be selected and/or adjusted based on motion of the display device.

[0100] The embodiments can be carried out by computer software implemented by the processor 152 or by hardware, or by a combination of hardware and software. As a non-limiting example, the embodiments can be implemented by one or more integrated circuits. The memory 154 can be of any type appropriate to the technical environment and can be implemented using any appropriate data storage technology, such as optical memory devices, magnetic memory devices, semiconductor-based memory devices, fixed memory, and removable memory, as non-limiting examples. The processor 152 can be of any type appropriate to the technical environment, and can encompass one or more of microprocessors, general purpose computers, special purpose computers, and processors based on a multi-core architecture, as non-limiting examples.

Block-Based Video Coding

[0101] Like HEVC, the WC is built upon the block-based hybrid video coding framework. FIG. 2A gives the block diagram of a block-based hybrid video encoding system 200. Variations of this encoder 200 are contemplated, but the encoder 200 is described below for purposes of clarity without describing all expected variations.

[0102] Before being encoded, a video sequence may go through pre-encoding processing (204), for example, applying a color transform to an input color picture (e.g., conversion from RGB 4:4:4 to YCbCr 4:2:0), or performing a remapping of the input picture components in order to get a signal distribution more resilient to compression (for instance using a histogram equalization of one of the color components). Metadata can be associated with the pre-processing and attached to the bitstream.

[0103] The input video signal 202 including a picture to be encoded is partitioned (206) and processed block by block in units of, for example, CUs. Different CDs may have different sizes. In VTM-1.0, a CD can be up to 128x128 pixels. However, different from the HEVC which partitions blocks only based on quad-trees, in the VTM- 1.0, a coding tree unit (CTU) is split into CUs to adapt to varying local characteristics based on quad/binary/ternary-tree. Additionally, the concept of multiple partition unit type in the HEVC is removed, such that the separation of CU, prediction unit (PU) and transform unit (TU) does not exist in the VVC-1.0 anymore; instead, each CU is always used as the basic unit for both prediction and transform without further partitions. In the multi-type tree structure, a CTU is firstly partitioned by a quad-tree structure. Then, each quad-tree leaf node can be further partitioned by a binary and ternary tree structure. Different splitting types may be used, such as quaternary partitioning, vertical binary partitioning, horizontal binary partitioning, vertical ternary partitioning, and horizontal ternary partitioning.

[0104] In the encoder of FIG. 2A, spatial prediction (208) and/or temporal prediction (210) may be performed. Spatial prediction (or “intra prediction”) uses pixels from the samples of already coded neighboring blocks (which are called reference samples) in the same video picture/slice to predict the current video block. Spatial prediction reduces spatial redundancy inherent in the video signal. Temporal prediction (also referred to as “inter prediction” or “motion compensated prediction”) uses reconstructed pixels from the already coded video pictures to predict the current video block. Temporal prediction reduces temporal redundancy inherent in the video signal. A temporal prediction signal for a given CU may be signaled by one or more motion vectors (MVs) which indicate the amount and the direction of motion between the current CU and its temporal reference. Also, if multiple reference pictures are supported, a reference picture index may additionally be sent, which is used to identify from which reference picture in the reference picture store (212) the temporal prediction signal comes.

[0105] The mode decision block (214) in the encoder chooses the best prediction mode, for example based on a rate-distortion optimization method. This selection may be made after spatial and/or temporal prediction is performed. The intra/inter decision may be indicated by, for example, a prediction mode flag. The prediction block is subtracted from the current video block (216) to generate a prediction residual. The prediction residual is de-correlated using transform (218) and quantized (220). (For some blocks, the encoder may bypass both transform and quantization, in which case the residual may be coded directly without the application of the transform or quantization processes.) The quantized residual coefficients are inverse quantized (222) and inverse transformed (224) to form the reconstructed residual, which is then added back to the prediction block (226) to form the reconstructed signal of the CU. Further in-loop filtering, such as deblocking/SAO (Sample Adaptive Offset) filtering, may be applied (228) on the reconstructed CU to reduce encoding artifacts before it is put in the reference picture store (212) and used to code future video blocks. To form the output video bit-stream 230, coding mode (inter or intra), prediction mode information, motion information, and quantized residual coefficients are all sent to the entropy coding unit (108) to be further compressed and packed to form the bitstream.

[0106] FIG. 2B gives a block diagram of a block-based video decoder 250. In the decoder 250, a bitstream is decoded by the decoder elements as described below. Video decoder 250 generally performs a decoding pass reciprocal to the encoding pass as described in FIG. 2A. The encoder 200 also generally performs video decoding as part of encoding video data.

[0107] In particular, the input of the decoder includes a video bitstream 252, which can be generated by video encoder 200. The video bit-stream 252 is first unpacked and entropy decoded at entropy decoding unit 254 to obtain transform coefficients, motion vectors, and other coded information. Picture partition information indicates how the picture is partitioned. The decoder may therefore divide (256) the picture according to the decoded picture partitioning information. The coding mode and prediction information are sent to either the spatial prediction unit 258 (if intra coded) or the temporal prediction unit 260 (if inter coded) to form the prediction block. The residual transform coefficients are sent to inverse quantization unit 262 and inverse transform unit 264 to reconstruct the residual block. The prediction block and the residual block are then added together at 266 to generate the reconstructed block. The reconstructed block may further go through in-loop filtering 268 before it is stored in reference picture store 270 for use in predicting future video blocks.

[0108] The decoded picture 272 may further go through post-decoding processing (274), for example, an inverse color transform (e.g. conversion from YCbCr 4:2:0 to RGB 4:4:4) or an inverse remapping performing the inverse of the remapping process performed in the pre-encoding processing (204). The post-decoding processing can use metadata derived in the pre-encoding processing and signaled in the bitstream. The decoded, processed video may be sent to a display device 276. The display device 276 may be a separate device from the decoder 250, or the decoder 250 and the display device 276 may be components of the same device.

[0109] Various methods and other aspects described in this application can be used to modify modules of a video encoder 200 or decoder 250. Moreover, the systems and methods disclosed herein are not limited to WC or HEVC, and can be applied, for example, to other standards and recommendations, whether pre-existing or future-developed, and extensions of any such standards and recommendations (including WC and HEVC). Unless indicated otherwise, or technically precluded, the aspects described in this application can be used individually or in combination.

[0110] FIG. 3A is a schematic side view illustrating an example waveguide display that may be used with extended reality (XR) applications according to some embodiments. An image is projected by an image generator 302. The image generator 302 may use one or more of various techniques for projecting an image. For example, the image generator 302 may be a laser beam scanning (LBS) projector, a liquid crystal display (LCD), a lightemitting diode (LED) display (including an organic LED (OLED) or micro LED (pLED) display), a digital light processor (DLP), a liquid crystal on silicon (LCoS) display, or other type of image generator or light engine.

[0111] Light representing an image 312 generated by the image generator 302 is coupled into a waveguide 304 by a diffractive in-coupler 306. The in-coupler 306 diffracts the light representing the image 312 into one or more diffractive orders. For example, light ray 308, which is one of the light rays representing a portion of the bottom of the image, is diffracted by the in-coupler 306, and one of the diffracted orders 310 (e.g. the second order) is at an angle that is capable of being propagated through the waveguide 304 by total internal reflection. The image generator 302 displays images as directed by a control module 324, which operates to render image data, video data, point cloud data, or other displayable data.

[0112] At least a portion of the light 310 that has been coupled into the waveguide 304 by the diffractive incoupler 306 is coupled out of the waveguide by a diffractive out-coupler 314. At least some of the light coupled out of the waveguide 304 replicates the incident angle of light coupled into the waveguide. For example, in the illustration, out-coupled light rays 316a, 316b, and 316c replicate the angle of the in-coupled light ray 308. Because light exiting the out-coupler replicates the directions of light that entered the in-coupler, the waveguide substantially replicates the original image 312. A user’s eye 318 can focus on the replicated image.

[0113] In the example of FIG. 3A, the out-coupler 314 out-couples only a portion of the light with each reflection allowing a single input beam (such as beam 308) to generate multiple parallel output beams (such as beams 316a, 316b, and 316c). In this way, at least some of the light originating from each portion of the image is likely to reach the user’s eye even if the eye is not perfectly aligned with the center of the out-coupler. For example, if the eye 318 were to move downward, beam 316c may enter the eye even if beams 316a and 316b do not, so the user can still perceive the bottom of the image 312 despite the shift in position. The out-coupler 314 thus operates in part as an exit pupil expander in the vertical direction. The waveguide may also include one or more additional exit pupil expanders (not shown in FIG. 3A) to expand the exit pupil in the horizontal direction.

[011 ] In some embodiments, the waveguide 304 is at least partly transparent with respect to light originating outside the waveguide display. For example, at least some of the light 320 from real-world objects (such as object 322) traverses the waveguide 304, allowing the user to see the real-world objects while using the waveguide display. As light 320 from real-world objects also goes through the diffraction grating 314, there will be multiple diffraction orders and hence multiple images. To minimize the visibility of multiple images, it is desirable for the diffraction order zero (no deviation by 314) to have a great diffraction efficiency for light 320 and order zero, while higher diffraction orders are lower in energy. Thus, in addition to expanding and out-coupling the virtual image, the out-coupler 314 is preferably configured to let through the zero order of the real image. In such embodiments, images displayed by the waveguide display may appear to be superimposed on the real world.

[0115] FIG. 3B is a schematic side view illustrating an example alternative display type that may be used with extended reality applications according to some embodiments. In an XR head-mounted display device 330, a control module 332 controls a display 334, which may be an LCD, to display an image. The head-mounted display includes a partly-reflective surface 336 that reflects (and in some embodiments, both reflects and focuses) the image displayed on the LCD to make the image visible to the user. The partly-reflective surface 336 also allows the passage of at least some exterior light, permitting the user to see their surroundings. [0116] FIG. 3C is a schematic side view illustrating an example alternative display type that may be used with extended reality applications according to some embodiments. In an XR head-mounted display device 340, a control module 342 controls a display 344, which may be an LCD, to display an image. The image is focused by one or more lenses of display optics 346 to make the image visible to the user. In the example of FIG. 3C, exterior light does not reach the user’s eyes directly. However, in some such embodiments, an exterior camera 348 may be used to capture images of the exterior environment and display such images on the display 344 together with any virtual content that may also be displayed.

[0117] The embodiments described herein are not limited to any particular type or structure of XR display device.

[0118] This application belongs to the field of point cloud compression and processing. This field aims to develop tools for compression, analysis, interpolation, representation and understanding of point cloud signals.

[0119] Point cloud is a universal data format across several business domains from autonomous driving, robotics, AR/VR, civil engineering, computer graphics, to the animation /movie industry. 3D LiDAR sensors have been deployed in self-driving cars, and affordable LiDAR sensors are released from Velodyne Velabit, Apple iPad Pro 2020 and Intel RealSense LiDAR camera L515. With advances in sensing technologies, 3D point cloud data becomes more practical than ever and is expected to be an ultimate enabler in the applications mentioned.

[0120] Point cloud data is also believed to consume a large portion of network traffic, e.g., among connected cars over 5G network, and immersive communications (VR/AR). Efficient representation formats are necessary for point cloud understanding and communication. In particular, raw point cloud data needs to be properly organized and processed for the purposes of world modeling & sensing. Compression on raw point clouds is essential when storage and transmission of the data are required in the related scenarios.

[0121] Furthermore, point clouds may represent a sequential scan of the same scene, which contains multiple moving objects. They are called dynamic point clouds as compared to static point clouds captured from a static scene or static objects. Dynamic point clouds are typically organized into frames, with different frames being captured at different times. Dynamic point clouds may require the processing & compression to be in real-time or with low delay.

[0122] The automotive industry and autonomous car are domains in which point clouds may be used. Autonomous cars should be able to “probe” their environment to make good driving decisions based on the reality of their immediate surroundings. Typical sensors like LiDARs produce (dynamic) point clouds that are used by the perception engine. These point clouds are not intended to be viewed by human eyes and they are typically sparse, not necessarily colored, and dynamic with a high frequency of capture. They may have other attributes like the reflectance ratio provided by the LiDAR as this attribute is indicative of the material of the sensed object and may help in making a decision.

[0123] Virtual Reality (VR) and immersive worlds have become a hot topic and foreseen by many as the future of 2D flat video. The basic idea is to immerse the viewer in an environment all around him as opposed to standard TV where he can only look at the virtual world in front of him. There are several gradations in the immersivity depending on the freedom of the viewer in the environment. Point cloud is a good format candidate to distribute VR worlds. They may be static or dynamic and are typically of average size, say no more than millions of points at a time.

[0124] Point clouds may also be used for various purposes such as culture heritage/buildings in which objects like statues or buildings are scanned in 3D to share the spatial configuration of the object without sending or visiting it. Also, it is a way to ensure preserving the knowledge of the object in case it may be destroyed, for instance, a temple by an earthquake. Such point clouds are typically static, colored, and huge.

[0125] Another use case is in topography and cartography in which using 3D representations, maps are not limited to the plane and may include the relief. Google Maps is now a good example of 3D maps but uses meshes instead of point clouds. Nevertheless, point clouds may be a suitable data format for 3D maps and such point clouds are typically static, colored, and huge.

[0126] World modeling & sensing via point clouds could be an essential technology to allow machines to gain knowledge about the 3D world around them, which is crucial for the applications discussed above.

[0127] The present application has been devised with the foregoing in mind.

[0128] 3D point cloud data are essentially discrete samples on the surfaces of objects or scenes. To fully represent the real world with point samples, in practice it requires a huge number of points. For instance, a typical VR immersive scene contains millions of points, while point clouds typically contain hundreds of millions of points. Therefore, the processing of such large-scale point clouds is computationally expensive, especially for consumer devices, e.g., smartphone, tablet, and automotive navigation system, that have limited computational power.

[0129] The first step for any processing or inference on the point cloud is to have efficient storage methodologies. To store and process the input point cloud with affordable computational cost, one solution is to down-sample it first, where the down-sampled point cloud summarizes the geometry of the input point cloud while having much fewer points. The down-sampled point cloud is then fed to the subsequent machine task for further consumption. However, further reduction in storage space can be achieved by converting the raw point cloud data (original or down sampled) into a bitstream through entropy coding techniques for lossless compression.

[0130] In addition to lossless coding, many scenarios seek for lossy coding for significantly improved compression ratio while maintaining the induced distortion under certain quality levels. To achieve a less lossy coding, an efficient point feature extractor is necessary to improve the accuracy of the reconstruction within the given resource budget.

Learning-Based Dynamic Point Cloud Compression

[0131] Rather than compressing point cloud frames independently, in practice, it is more demanding to compress a dynamic point cloud sequence consisting of a series of frames. Inter-frame prediction has thus been introduced for point cloud compression including point cloud geometry as well as point cloud attributes to exploit temporal redundancies.

[0132] A specific challenge of learning based inter-frame prediction for dynamic point cloud is how to conduct predictions for a current frame based on reference frames and how to utilize the generated predictions to code a current frame.

[0133] Dynamic point clouds, that are captured by LiDAR within autonomous driving or captured for VR/AR applications, may impose great challenges when being stored or transmitted due to a huge amount of data. In this application, we attempt to tackle the challenges in deep learning based dynamic point cloud compression. We specifically study how to perform inter-frame predictions using deep learning techniques. Two challenges to be addressed: how to produce a prediction based on the reference point cloud frames; and how to utilize the prediction to assist the coding of the current frame. The proposed technology in this application is called explicit predictive coding given an explicit motion analysis to be present.

[0134] This application provides an inter-frame predictive coding for dynamic point cloud compression. The proposal is referenced as an explicit prediction technique as it is characterized by having an explicit motion analysis on encoder, and an explicit decoding of motion information on decoder. In prior explicit prediction techniques, when their predictor feature is produced, a predictor point cloud frame in 3D space is constructed. Such predictor frame construction involves a point cloud synthesis step which may involve a heavy network. In this application, it is proposed to produce the predictor feature without constructing a predictor frame. Instead, the predictor feature is directly computed based on the reference frame and motion features. Finally, a two-level conditional coding paradigm is deployed to compress the current point cloud frame conditioned on the motion feature and then on the predictor feature.

Encoder and Decoder

[0135] FIG. 4 is a process diagram illustrating an example codec encoding and decoding process with explicit prediction according to some embodiments. FIG. 4 illustrates the overall diagram 400 of the proposed Interframe prediction coding for dynamic point clouds with an explicit prediction. The left side of FIG. 4 is the encoder section 402, and the right side is the decoder section 404.

Encoder

[0136] The encoding portion 402 of FIG. 4 includes three sections. The first section is for motion analysis which is used to analyze the dynamics between the two point cloud frames. This section takes the current point cloud PC_CURR and the reference point cloud PC_REF as input. A motion analysis is conducted on this pair of point cloud frames by an MA block 406, which outputs a motion feature map F_m as a descriptor for the motion between the reference point cloud frame and the current point cloud frame. Note that F_m is a feature map, with each feature being associated with a point or a partition (the spatial resolution may be changed based on MA architecture) in a point cloud frame. Then, the motion feature F_m is entropy encoded by an ENCm block 408, which outputs a motion bitstream BS_m and a reconstructed motion feature F_m which is the quantized version of F_m. Note that the motion information is outputted and coded in a feature domain as a feature map rather than in a 3D spatial domain as motion vectors. By representing motion in the feature domain, the dimension of the feature vectors typically have a much higher dimension than the 3-dim of the 3D world, e.g., the feature vectors may be 16-dimensional vectors. Therefore, compared to the raw motion vectors with 3 dimensions, the highdimensional motion feature is more friendly for compression with higher representability. Hence, in the motion analysis section, 3D motion field containing raw 3D motion vectors is not necessarily to be generated.

[0137] The second section, a predictor feature generator block 410, takes the reference point cloud frame PC_REF and the reconstructed motion feature F_m as input. A predictor feature map F_P is then generated.

[0138] The third section is known as the coding section, or deep feature-based coding section. This section is mainly composed of two steps. A feature encoder I feature extraction step FE is followed by an entropy encoding. The FE block 412 takes the current point cloud PC_CURR as its main input and outputs a feature map F_M. The entropy coding starts with a rounding or quantization to allow entropy (arithmetic) coding on a sequence of symbols. A bitstream BS_M is then generated by an encoder (ENC_M) block 414. Moreover, in this application, the feature extraction block is restricted by a condition input (see 798 and ‘130 applications) that is the predictor feature map F_P. Later, on the decoding side, the same condition will be applied on a corresponding decoding block. Overall, a conditional autoencoder architecture is employed in the proposed method.

[0139] Note that the predictor generation FA block 410, 418 is restricted by a condition feature map F_m. At the same time, FA’s output is used as a condition for the (main) coding section. Thus, the proposed architecture in FIG. 4 may be referred to as a 2^nd-order conditional autoencoder.

Decoder

[0140] The decoding portion 404 of FIG. 4 is composed of three sections corresponding to the decoding sections. These three sections are the motion reconstruction section, the predictor feature generation section, and the deep-feature based decoding section. The basic idea is to first decode the motion from BS_m with the motion reconstruction section, then compute the predictor feature based on the reference frame PC_REF with the feature generation section, followed by decoding the reconstructed point cloud with the deep-feature based decoding section.

[0141] The first section is the motion reconstruction section. There is no motion analysis step on the decoding side. Instead, an entropy decoder (DEC_m) 416 reconstructs the motion feature map F_m from the bitstream BS_m.

[0142] The second section of decoding is exactly the same as the second section of encoding, which is a predictor feature generation FA block 418. The FA block 418 of the decoder takes the same inputs as the FA block 410 of the encoder, which are the reference point cloud frame PC_REF and the reconstructed motion feature F_m. Hence, the same predictor feature map F_P is reproduced at the decoder.

[0143] The third section of decoding, deep feature-based decoding, includes two steps. The entropy decoding (DEC_M) 420 decodes the bitstream BS_M to reconstruct the feature map F_M. A feature aggregation is conducted by a feature decoder FD 422 to reconstruct the point cloud PC_CURR based on the feature map F_M. As pointed out earlier, the feature decoder FD 422 is restricted by the predictor feature map F_P as a condition.

[0144] The diagram for inter-frame predictive coding is characterized by having a bitstream dedicated for motion information. This leads to an asymmetric architecture design that allows a lighter decoder and a heavier encoder. The reason is that the motion analysis is typically computation intensive, that is only required during encoding. For the decoder, it directly decodes the motion information to build the motion information, and then the predictor information. The decoding of motion information from a bitstream is typically much easier task than the motion analysis. On the other hand, by performing motion analysis and send motion information as an overhead in the bitstream, it generally provides higher quality of predictor feature map comparing to an implicit prediction approach where the predictor is created purely based on a reference frame.

[0145] The diagram for inter-frame predictive coding is additionally characterized by a conditional autoencoder architecture. In the main coding section, both the encoder and decoder are restricted by the same condition input.

Motion Analysis

[0146] As presented earlier, the motion analysis MA outputs a motion feature map instead of a motion field considering the feature map is easier to be compressed while more representative. However, it may be challenging to train such a motion analysis block which outputs a motion feature map rather than directly outputting a motion field, which is to be addressed next.

[0147] FIG. 5 is a process diagram illustrating an example training process for the motion analysis according to some embodiments. In some embodiments of a training process 500, the motion analysis block MA 502 is pre-trained before training the codec in FIG. 4 end-to-end. The pre-training method for the MA block 502 is proposed as shown in FIG. 5. In some embodiments, a motion synthesis block MS is employed to enable the training of motion analysis. Particularly, the MS block is appended after the MA block 502 and the (ENC_m) block 504. The MS block 506 takes F_m as input and generates a 3D motion field M_m. M_m contains the 3-D motion vectors between PC_CURR and PC_REF for each point in PC_CURR . Having introduced the MS block, the pretraining of the MA block may be performed by supervising the motion field M_m with the ground truth motion field.

[0148] For some embodiments, the MS block 506 is introduced for pre-training of the MA block 502. Once the pre-training is done, the MS block 506 is no longer used elsewhere. The ground-truth motion field is the true, correct motion between the current and the reference point clouds. The ground truth is used for pre-training the MA block.

[0149] To perform such training, off-the-shelf datasets for motion or scene flow estimation may be used so that the ground-truth motion field describing the true motion between PC_CURR and PC_REF is available. In the case of when the ground truth motion field does not exist, a self-supervised training strategy may be used to train the MA block. The strategy is as follows for some embodiments. During each training step, a motion field M_m is computed. Then PC_CURR is swapped with the reference point cloud PC_REF as inputs to the MA block to get another motion field The self-supervised training strategy is that, if the MA block 502 and MS block 506 operates properly, then the motions in M’_n should be in the opposite directions of M_m. Therefore, a consistency metric may be computed between M_m' and -M_m as a loss function fortraining purpose. In some embodiments, the Chamfer Distance for point sets is used as the consistency metric such that Loss = CD(M,'_n, -M_m), where CD denotes Chamfer Distance.

[0150] In the example of FIG. 5, the MS block takes F_m as an input that undergoes some distortion from rounding or quantization for an entropy coding. In such a way, the rounding or quantization effect may be taken into account in the pre-training. However, it is noted that the rounding/quantization is non-differentiable and prevents backward propagation. In the end, such distortion is simulated by adding noise signals for training purposes. In some embodiments, the MS block takes the motion feature F_m directly as an input and generates the motion field M_m. Once the pre-training of the MS block is finished, its neural network parameters will be loaded in the proposed codec (FIG. 4). The MS block is introduced for pre-training of the MA block. Thus, once the pre-training is finished, the MS block is no longer being used. That is why the MS block does not appear in FIG. 4. For some embodiments, the output of the MA block is fed directly into the MS block.

[0151] FIG. 6 is a process diagram illustrating an example training process for a predictor feature generation block according to some embodiments. An example training method 600 is shown in FIG. 6. For some embodiments, the FA block 602 may be trained using a dedicated step. A feature synthesis (FS) block 604 takes the feature map F_P as an input and synthesizes a point cloud PC in 3D space.

[0152] FIG. 7 is a process diagram illustrating an example motion analysis process according to some embodiments. FIG. 7 shows an example design of an motion analysis (MA) block 700. Firstly, the reference point cloud frame and the current point cloud frame are sent to the same spatial feature extraction FB block 702, 704 to output spatial feature maps F_{S 1} and F_{s 2}. The spatial features are typically associated with a downsampled point cloud. They are abstract, high-level descriptors that may be leveraged by subsequent modules to extract motion information. For some embodiments, the fusing (FU) block 706 may sum up and/or concatenate the feature maps.

[0153] Then a fusing (FU) block 706 is applied to fuse the two spatial feature maps. For each position in the current feature map F_{s 2}, the motion analysis process looks for its k nearest neighbors in the reference feature map F_{s l}. Suppose a position A in F_{s 2} has a feature vector with its k nearest neighboring positions in the reference feature map F_{S 1} are associated with feature vectors f ⁾ , on F_{s l}. In one embodiment, the FU block concatenates with all the vectors f -* , f ²⁾ , ... , the position A. This is performed for not only the position A but also all the other positions in F_{s 2}. The concatenated feature map, denoted by F_T, would be output by FU block 706. In some embodiments, the FU block 706 sums up and all of the vectors f ) , f ²⁾ , ... , f₁ ^(fc) at the position A. Again, this is performed for not only the position A but also all the other positions in F_SI2. The summed feature map F_T would be output by FU block. Note that after the fusing step by FU block, the output feature map contains information from both the PC_CURR and PC_REF.

[0154] Last, a feature aggregation FC is performed to further aggregate the temporal feature maps from the FU block 706. In one example, the FC block 708 is implemented using four (4) convolutional layers before outputting the motion feature F_m. The dimensions of the convolutional layers are (128, 128, 64, 64, 32) so the motion feature map F_m have 32 channels. See FIG. 10 for its process diagram.

Spatial Feature Extractor

[0155] We hereby discuss the design of the spatial feature extractor block FB. The spatial feature extractor FB takes a point cloud PC_INP as input and outputs its feature map.

[0156] FIG. 8 is a process diagram illustrating an example feature extraction for voxel-based representation according to some embodiments. In some embodiments when PC_CURR and PC_REF are voxelized point clouds, the FB block 800 is composed of two convolutional layers 806, 808 (with stride two for downsampling) and two multi-layer perceptron (MLP) layers 802, 804, as shown in FIG. 8. For example, these four layers have inputoutput dimensions of (3, 32, 64, 128, 64) so that the output feature maps F_{S 1} and F_{s 2} would both have 64 channels.

[0157] FIG. 9 is a process diagram illustrating an example feature extraction for point-based representation according to some embodiments. In another embodiment when PC_CURR and PC_REF are represented with the point-based representation, the design of an FB block 900 is provided in FIG. 9. In this embodiment, the FB block 900 first performs block partitioning 902 to divide the point clouds uniformly into blocks, followed by applying a shared blockwise feature extractor PN 904 to compute a feature vector for each block. All such blockwise features constitute the output feature map of FB. In some embodiments, the PN block 904 takes the design of PointNet. See Qi, Charles R., et al. Pointnet: Deep Learning on Point sets for 3D Classification and Segmentation, PROCEEDINGS OF THE IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (2017). It consists of a few pointwise MLP layers with dimensions of (3, 32, 64, 128, 128) and a global max pooling to obtain a block feature with 128 channels. It is then followed by three MLP layers with dimensions of (128, 64, 64) so that the output feature maps F_{S 1} and F_{s 2} have 64 channels.

Predictor Generation

[0158] In the second section, both encoder and decoder share a same design of predictor generation block. The predictor generation plays an important role for inter-frame prediction to benefit the compression.

[0159] In one embodiment, a point cloud frame predictor in 3D space is explicitly generated in the middle of the predictor generation FA block. Examples are described in the 798 and ‘130 applications.

[0160] However, in this application, we propose to avoid generating point cloud frame in 3D space in the middle of FA block. One motivation is that the FA block needs to run on both encoder and decoder, the complexity is desired to be reduced as much as possible. On the other hand, synthesizing a point cloud in 3D space from feature space may be a rather computation intensive task. Consequently, in one example, we propose not to synthesize a point cloud during the predictor generation procedure. However, it will introduce extra challenge how to train the FA block.

[0161] In this application, we propose to pre-train the FA block using a dedicated step. The training method is shown in FIG. 6. We introduce a feature synthesis block FS for the training purpose. The FS block takes the feature map F_P as an input and synthesizes a point cloud PC in 3D space. The supervision is conducted using an error metric between the synthesized point cloud PC' and the current point cloud PC_CURR.

[0162] In one embodiment, when the dimensionality of the predictor feature F_P is aligned with the feature F_m, the feature decoder FD block may be used as the FS block.

[0163] Note that both the motion analysis block in FIG. 5 and the predictor generation block in FIG. 6 may be viewed as an “encoding” network. In order to train those “encoding” network, we use a dedicated “decoding” network to enable the training procedure. It should be noted that a better selection of the “decoding” network may help us getting a better “encoding” network due to the backward propagation mechanism.

[0164] FIG. 10 is a process diagram illustrating an example feature aggregation (FC block) according to some embodiments. For some embodiments, the FC block of FIG. 7 may be implemented as shown in the example FC block 1000 FIG. 10. An output of the FU block of FIG. 7 is designated as input feature map F_T in FIG. 10. The feature map F_T may be passed through a series of convolutional coders 1002, 1004, 1006, 1008 and outputted as motion feature map F_m. FIG. 10 shows 4 convolutional coders, but the quantity may be different for some embodiments.

[0165] FIG. 11 is a process diagram illustrating an example feature predictor generation (FA block) according to some embodiments. FIG. 11 shows an example design of the predictor generation block 1100. Firstly, feature map F_{S 1} is extracted for the reference point cloud frame PC_REF using a spatial feature extractor FB 1102. The FB block 1102 may be the same design of the FB block 702, 704 in FIG. 7 for motion analysis. Then the feature F_{S 1} is concatenated (the symbol 1104 in FIG. 11) with the motion feature F_m that is followed by a series of MLPs 1106, 1108 and convolutional layers 1110, 1112 to output the predictor feature map F_P. The dimensions of the layers in FIG. 11 are (128, 256, 256, 64).

[0166] In some embodiments, IRN or transformer blocks may be used to enhance the feature aggregation. See Szegedy, Christian, et al., Inception-v4, inception-resnet and the impact of residual connections on learning, 31 :1 IN PROCEEDINGS OF THE AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE (2017) ‘Szeged )-, Zhao, Hengshuang, et al., Point Transformer, ICCV 16239-16248 (2021) (“Zhao”); Mao, Jiageng, et al., Voxel transformer for 3d object detection, IN PROCEEDINGS OF THE IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION 3164-3173 (2021) (“Mao”); and Zhang, Cheng, et al., PVT: Point-Voxel Transformer for Point Cloud Learning, arXiv preprint arXiv: 2108.06076 (2021) ‘Zhang’’).

Feature Encoder

[0167] FIG. 12 is a process diagram illustrating an example feature aggregation/extraction in the encoder (FE block) according to some embodiments. In the third section, the encoder and decoder have a symmetric design. They perform encoding and decoding condition on the predictor feature map F_P. In this subsection, an example of the conditional feature encoder FE 1200 is provided, see FIG. 12.

[0168] Firstly, the current point cloud PC_CURR is first fed to a FB block 1202 for initial feature extraction, leading to the output F_SI2. It is then concatenated with the predictor feature F_P. Suppose both F_SI2 and F_P have 64 channels, then the concatenated feature has 128 channels in total. It is then passed to a few neural network layers to generate the output feature map F_u . The purpose of these layers is to remove the redundant information in both F_{s 2} and F_P from F_{s 2} so that the resulting feature map F_M contains less information, and leads to a smaller bitstream BS_M.

[0169] In one embodiment, we let these layers be a series of MLPs 1204, 1206 and convolutional layers 1208, 1210 to output the feature map F_M . The dimensions of the four layers in FIG. 12 are (128, 256, 256, 64), so that F_M have 64 channels. In other embodiments, IRN or advanced transformer may be used to replace the convolutional layers or MLP layers to enhance the feature encoder. See Szegedy Zhao,' Mao', and Zhang.

[0170] Instead of the concatenation operation followed by a redundancy removal between the predictor feature map F_P and the spatial feature map F_s, one may perform a direct residual computation. It may be preferred considering its simplicity. However, the direct residual computation may be less efficient in compression and a dedicated neural network layer may be more efficient to remove the temporal redundancy.

Feature Decoder

[0171] FIG. 13 is a process diagram illustrating an example feature aggregation/extraction in the decoder (FD block) according to some embodiments. In this subsection, we illustrate the design of the conditional feature decoder FD 1300, as shown in FIG. 13. Firstly, the decoded feature map F_M is concatenated with the condition, the predictor feature map F_P. Suppose both F_M and F_P have 64 dimensions, then the concatenated feature has 128 dimensions. The concatenated feature is fed to a few neural network layers to generate the feature map F_{s 2}. Via this processing, the predictor information based on reference frame is able to be fused back into feature map F_{s 2}. In some embodiments, these layers are a series of MLPs 1302, 1304 and convolutional layers 1306, 1308 to output the feature map F_{s 2}.The dimensions of the four layers in FIG. 13 are (128, 256, 256, 64), so that F_{S 2} have 64 channels. In some embodiments, IRN or advanced transformer may be used to replace the convolutional layers or MLP layers to enhance the feature decoder. See Szegedy, Zhao,' Mao', and Zhang. After that, the feature F_{s 2} is fed to a point synthesis PS block 1310 to reconstruct the current point cloud PC_CURR ^IN 3D space.

[0172] FIG. 14 is a process diagram illustrating an example feature aggregation/extraction in the decoder (FD block) according to some embodiments. In some embodiments, as shown in FIG. 14, the concatenation happens a bit later in the pipeline. The entropy decoded feature map F_M serves as an input, that is processed by a series of convolutional layers 1402, 1404 and MLPs 1406, 1408. Then the aggregated feature is concatenated by the predictor feature map F_P. Finally, the concatenated feature F_s is sentto a point synthesis PS block to synthesize the point cloud in 3D space. In this example implementation, the fusion of predictor information is postponed to the point synthesis PS block 1410.

[0173] FIG. 15 is a process diagram illustrating an example conditional feature decoder according to some embodiments. In some embodiments of the example feature decoder 1500 of FIG. 15, the fusion of predictor information may be performed before processing through the PS block 1518 by connecting another series of convolutional layers/CNNs 1502, 1504, 1514, 1516 and MLPs 1506, 1508, 1510, 1512 after the concatenation. In this case, series of convolutional layers/CNNs 1502, 1504, 1514, 1516 and MLPs 1506, 1508, 1510, 1512 may be located both before and after the feature maps concatenation.

[0174] FIG. 16 is a process diagram illustrating an example point synthesis block (PS block) according to some embodiments. We hereby provide the design of the PS block 1600. In one embodiment, if it is desired to reconstruct PC_CURR in point-based representation, the point synthesis block consists of 2 convolutional layers 1602, 1604 and 2 MLP layers 1606, 1608, as shown in FIG. 16. The dimensions of the four layers in FIG. 16 are (128, 256, 256, 5*3), so that each feature vector in F_{s 2} leads to 5 (five) 3D points in the reconstructed current point cloud PCCURR ■ In another embodiment, if it is desired to reconstruct PC_CURR in voxel-based representation, the point synthesis block contains only convolutional layers, the same as the decoder design in Wang, Jianqiang, et al., Multiscale Point Cloud Geometry Compression, 2021 DATA COMPRESSION CONFERENCE (DCC). IEEE (2021) and the 798 application.

End-to-end Training

[0175] The proposed explicit predictive coding network needs to be trained over a dynamic point cloud sequence dataset. A training method may include pre-training the motion analysis block MA as described above in FIG. 5 and pre-training the predictor generation block FA in FIG. 6 as described above. Based on the pretrained motion analysis MA and predictor generation FA, the full architecture (FIG. 4) is trained in an end-to-end manner. In some embodiments, the MA and the FA blocks may be trained end-to-end from scratch together with the other blocks. For some embodiments, the MA and FA blocks may be pre-trained. During the end-to-end training, a routine practice is to replace the entropy coding/decoding steps with an entropy bottleneck layer. See Balle, Johannes, er al., Variational image compression with a scale hyperprior, INTERNATIONAL CONFERENCE ON LEARNING REPRESENTATIONS (2018); and David Minnen, et al., Joint Autoregressive and Hierarchical Priors for Learned Image Compression, ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS (2018). In actual training, the rate and the distortion are jointly minimized. Thus, the bitrate budget may be modeled in a differentiable manner to optimize the codec. An entropy bottleneck layer serves this purpose. The entropy bottleneck estimates the bitrate of the input feature map in a differentiable manner, so as to enable end-to-end training of the feature compression pipeline. In some embodiments, two entropy bottleneck layers may be used. Particularly, one entropy bottleneck layer is used to estimate the rate of motion information and the second one is used to estimate the feature rate in the main coding section.

Advanced Feature Aggregation

[0176] In the application, we use MLPs and convolutional layers as basic micro-architectures as an elementary design of the proposed functional architecture. It should be noted that they may be replaced or appended with advanced feature aggregation micro-architectures, for example Inception ResNets (IRNs) or transformer blocks. See Szegedy, Zhao,' Mac, and Zhang.

Inception ResNet (IRN)

[0177] FIG. 17 is a process diagram illustrating an example Inception-ResNet block for feature aggregation according to some embodiments. The IRN architecture 1700 is provided in FIG. 17. This example shows the architecture of an IRN block 1700 to aggregate features with D channels. Here “CON /V” means a convolutional layer that accepts an input with N channels. In this example, each CONV D/4 block 1702, 1706, 1712 is followed by a Recti-Linear Unit (ReLU) block 1704, 1708, 1714. The output of each of the CONV D/2 blocks 1710, 1716 is concatenated together by a concatenation block 1718. The plus symbol (“®”) 1720 denotes summation.

Transformer

[0178] FIG. 18 is a process diagram illustrating an example transformer block for feature aggregation according to some embodiments. The diagram of a transformer block 1800 is shown in FIG. 18, where again, (1804, 1808) denotes summation. FIG. 18 shows the basic diagram of a transformer block 1800, which consists of a self-attention block 1802 with residual connection, and a MLP block 1806 (consisting of a few MLP layers) with residual connection.

[0179] FIG. 19 is a process diagram illustrating an example self-attention block according to some embodiments. The block diagram of the self-attention block 1900 is shown in FIG. 19. Its details are described below. [0180] Given a current feature vector f_A (1902) associated with a voxel location A, and its neighboring k features f_Ai associated with voxel locations A_it where A_t (0 < i < k - 1) are the k nearest neighbors of A in the input sparse tensor, the self-attention block 1900 endeavors to update the feature f_A (1902) based on all the neighboring features f_4i (1910). Firstly, the points A_t (1904) are obtained by passing the feature f_A (1902) through a kNN block 1926 to perform a k nearest neighbor (kNN) search based on the coordinate of A. Then the query embedding Q_A for A is computed with:

QA = MLP_Q (f , in which the current feature vector f_A (1902) is passed through an MLP block 1906 to generate Q_A (1908).

[0181] After that, the key embedding K_A. (1920) and the value embedding V_A. (1922) of all the nearest neighbors of A are computed: where MLPQ(-) (1906), MLPK(-) (1912), and MLPv(-) (1914) are MLP layers to obtain the query, key, and value respectively, and E_A. (1918) is the positional encoding between the voxels A and A, calculated by: where MLPp( ) (1916) is MLP layers to obtain the positional encoding, PA and PAI are 3-D coordinates, they are centers of the voxels A and A/, respectively. The output feature of location A by the self-attention block is: where cr(-) is the Softmax normalization function, d is the length of the feature vector fz\ and c is a pre-defined constant.

[0182] The transformer block updates the feature map for all locations in the same way and then outputs the updated feature map. Note that in a simplified embodiment, MLPQ(-), MLPK( ), MLPV< ), and MLPp(-) may contain only one fully-connected layer, which corresponds to linear projections.

[0183] FIG. 20 is a flowchart illustrating an example decoding process according to some embodiments. For some embodiments, an example process 2000 may include obtaining 2002 a previously decoded point cloud frame as a reference point cloud frame. For some embodiments, the example process 2000 may further include obtaining 2004 a motion feature that describes a motion between the reference point cloud frame and a current point cloud frame. For some embodiments, the example process 2000 may further include determining 2006 a predictor feature map based on the reference point cloud frame and the motion feature. For some embodiments, the example process 2000 may further include obtaining 2008 a current feature map that represents the current point cloud frame given the predictor feature map as a condition. For some embodiments, the example process 2000 may further include reconstructing 2010 the current point cloud frame based on the current feature map and using the predicted feature as a condition.

[0184] FIG. 21 is a flowchart illustrating an example encoding process according to some embodiments. For some embodiments, an example process 2100 may include obtaining 2102 a previously encoded point cloud frame as a reference point cloud frame. For some embodiments, the example process 2100 may further include obtaining 2104 a motion feature that describes motion between the reference point cloud frame and a current point cloud frame. For some embodiments, the example process 2100 may further include determining 2106 a predictor feature map based on the reference point cloud frame and the motion feature. For some embodiments, the example process 2100 may further include determining 2108 a current feature map that represents the current point cloud frame given the predictor feature map as a condition. For some embodiments, the example process 2100 may further include encoding 2110 the current feature map into a bitstream using the predictor feature as a condition.

[0185] While the methods and systems in accordance with some embodiments are generally discussed in context of extended reality (XR), some embodiments may be applied to any XR contexts such as, e.g., virtual reality (VR) / mixed reality (MR) I augmented reality (AR) contexts. Also, although the term “head mounted display (HMD)” is used herein in accordance with some embodiments, some embodiments may be applied to a wearable device (which may or may not be attached to the head) capable of, e.g., XR, VR, AR, and/or MR for some embodiments.

[0186] A first example method/apparatus in accordance with some embodiments may include: obtaining a previously decoded point cloud frame as a reference point cloud frame; obtaining a motion feature that describes a motion between the reference point cloud frame and a current point cloud frame; determining a predictor feature map based on the reference point cloud frame and the motion feature; obtaining a current feature map that represents the current point cloud frame given the predictor feature map as a condition; and reconstructing the current point cloud frame based on the current feature map and using the predictor feature as a condition.

[0187] For some embodiments of the first example method, obtaining the motion feature that describes motion between the reference point cloud frame and the current point cloud frame includes: performing motion analysis to generate a motion feature map using the reference point cloud frame and the current point cloud frame as inputs; and entropy encoding the motion feature map to generate the motion feature.

[0188] For some embodiments of the first example method, obtaining the motion feature that describes motion between the reference point cloud frame and the current point cloud frame includes: performing a feature extraction on the reference point cloud frame to generate a first feature map; performing a feature extraction on the current point cloud frame to generate a second feature map; fusing the first and second feature maps to generate a fused feature map; and performing a feature aggregation on the fused feature map to generate the motion feature.

[0189] For some embodiments of the first example method, wherein the reference point cloud frame and the current point cloud frame are voxel-based representations, and wherein performing the feature extraction on the reference point cloud frame includes: passing the reference point cloud frame through one or more multi-layer perceptron (MLP) blocks; and passing an output of the one or more MLP blocks through one or more convolutional layers to generate the first feature map, and wherein performing the feature extraction on the current point cloud frame includes: passing the current point cloud frame through one or more multi-layer perceptron (MLP) blocks; and passing an output of the one or more MLP blocks through one or more convolutional layers to generate the second feature map.

[0190] For some embodiments of the first example method, wherein the reference point cloud frame and the current point cloud frame are point-based representations, and wherein performing the feature extraction on the reference point cloud frame includes: performing a block partition on the reference point cloud frame; and performing a blockwise feature extraction on the block partitioned reference point cloud frame to generate the first feature map, and wherein performing the feature extraction on the current point cloud frame includes: performing a block partition on the current point cloud frame; and performing a blockwise feature extraction on the block partitioned current point cloud frame to generate the second feature map.

[0191] For some embodiments of the first example method, obtaining the motion feature includes performing motion analysis training.

[0192] For some embodiments of the first example method, determining the predictor feature map based on the reference point cloud frame and the motion feature includes: performing a feature extraction on the reference point cloud frame to generate a first feature map; concatenating the first feature map with the motion feature; passing the concatenated first feature map through one or more multi-layer perceptron (MLP) blocks; and passing an output of the one or more MLP blocks through one or more convolutional layers to generate the predictor feature map.

[0193] For some embodiments of the first example method, wherein performing the feature extraction on the reference point cloud frame includes performing a point synthesis.

[0194] For some embodiments of the first example method, wherein performing the feature extraction on the current point cloud frame includes performing a point synthesis.

[0195] A first example method/apparatus in accordance with some embodiments may include: a processor; and a non-transitory computer-readable medium storing instructions operative, when executed by the processor, to cause the apparatus to perform any one of the methods listed above.

[0196] A second example method/apparatus in accordance with some embodiments may include: obtaining a previously encoded point cloud frame as a reference point cloud frame; obtaining a motion feature that describes motion between the reference point cloud frame and a current point cloud frame; determining a predictor feature map based on the reference point cloud frame and the motion feature; determining a current feature map that represents the current point cloud frame given the predictor feature map as a condition; and encoding the current feature map into a bitstream using the predictor feature as a condition.

[0197] For some embodiments of the second example method, obtaining the motion feature that describes motion between the reference point cloud frame and the current point cloud frame includes: performing motion analysis to generate a motion feature map using the reference point cloud frame and the current point cloud frame as inputs; and entropy encoding the motion feature map to generate the motion feature.

[0198] For some embodiments of the second example method, obtaining the motion feature that describes motion between the reference point cloud frame and the current point cloud frame includes: performing a feature extraction on the reference point cloud frame to generate a first feature map; performing a feature extraction on the current point cloud frame to generate a second feature map; fusing the first and second feature maps to generate a fused feature map; and performing a feature aggregation on the fused feature map to generate the motion feature.

[0199] For some embodiments of the second example method, wherein the reference point cloud frame and the current point cloud frame are voxel-based representations, and wherein performing the feature extraction on the reference point cloud frame includes: passing the reference point cloud frame through one or more multilayer perceptron (MLP) blocks; and passing an output of the one or more MLP blocks through one or more convolutional layers to generate the first feature map, and wherein performing the feature extraction on the current point cloud frame includes: passing the current point cloud frame through one or more multi-layer perceptron (MLP) blocks; and passing an output of the one or more MLP blocks through one or more convolutional layers to generate the second feature map.

[0200] For some embodiments of the second example method, wherein the reference point cloud frame and the current point cloud frame are point-based representations, and wherein performing the feature extraction on the reference point cloud frame includes: performing a block partition on the reference point cloud frame; and performing a blockwise feature extraction on the block partitioned reference point cloud frame to generate the first feature map, and wherein performing the feature extraction on the current point cloud frame includes: performing a block partition on the current point cloud frame; and performing a blockwise feature extraction on the block partitioned current point cloud frame to generate the second feature map.

[0201] For some embodiments of the second example method, obtaining the motion feature includes performing motion analysis training.

[0202] For some embodiments of the second example method, determining the predictor feature map based on the reference point cloud frame and the motion feature includes: performing a feature extraction on the reference point cloud frame to generate a first feature map; concatenating the first feature map with the motion feature; passing the concatenated first feature map through one or more multi-layer perceptron (MLP) blocks; and passing an output of the one or more MLP blocks through one or more convolutional layers to generate the predictor feature map.

[0203] For some embodiments of the second example method, determining the current feature map includes: performing a feature extraction on the current point cloud frame to generate a second feature map; concatenating the second feature map with the predictor feature map; passing the concatenated second feature map through one or more multi-layer perceptron (MLP) blocks; and passing an output of the one or more MLP blocks through one or more convolutional layers to generate the current feature map.

[0204] For some embodiments of the second example method, performing the feature extraction on at least one of the reference point cloud frame and the current point cloud frame includes using an Inception-ResNet block. [0205] A second example method/apparatus in accordance with some embodiments may include: a processor; and a non-transitory computer-readable medium storing instructions operative, when executed by the processor, to cause the apparatus to perform any one of the methods listed above.

[0206] A third example apparatus in accordance with some embodiments may include at least one processor configured to perform any one of the methods listed above.

[0207] A fourth example apparatus in accordance with some embodiments may include a computer-readable medium storing instructions for causing one or more processors to perform any one of the methods listed above.

[0208] A fifth example apparatus in accordance with some embodiments may include at least one processor and at least one non-transitory computer-readable medium storing instructions for causing the at least one processor to perform any one of the methods listed above.

[0209] An example signal in accordance with some embodiments may include a bitstream generated according to any one of the methods listed above.

[0210] This application describes a variety of aspects, including tools, features, embodiments, models, approaches, etc. Many of these aspects are described with specificity and, at least to show the individual characteristics, are often described in a manner that may sound limiting. However, this is for purposes of clarity in description, and does not limit the application or scope of those aspects. Indeed, all of the different aspects can be combined and interchanged to provide further aspects. Moreover, the aspects can be combined and interchanged with aspects described in earlier filings as well.

[0211] The aspects described and contemplated in this application can be implemented in many different forms. While some embodiments are illustrated specifically, other embodiments are contemplated, and the discussion of particular embodiments does not limit the breadth of the implementations. At least one of the aspects generally relates to video encoding and decoding, and at least one other aspect generally relates to transmitting a bitstream generated or encoded. These and other aspects can be implemented as a method, an apparatus, a computer readable storage medium having stored thereon instructions for encoding or decoding video data according to any of the methods described, and/or a computer readable storage medium having stored thereon a bitstream generated according to any of the methods described.

[0212] In the present application, the terms “reconstructed” and “decoded” may be used interchangeably, the terms “pixel” and “sample” may be used interchangeably, the terms “image,” “picture” and “frame” may be used interchangeably. Usually, but not necessarily, the term “reconstructed” is used at the encoder side while “decoded” is used at the decoder side.

[0213] The terms HDR (high dynamic range) and SDR (standard dynamic range) often convey specific values of dynamic range to those of ordinary skill in the art. However, additional embodiments are also intended in which a reference to HDR is understood to mean “higher dynamic range” and a reference to SDR is understood to mean “lower dynamic range.” Such additional embodiments are not constrained by any specific values of dynamic range that might often be associated with the terms “high dynamic range” and “standard dynamic range.”

[0214] Various methods are described herein, and each of the methods comprises one or more steps or actions for achieving the described method. Unless a specific order of steps or actions is required for proper operation of the method, the order and/or use of specific steps and/or actions may be modified or combined. Additionally, terms such as “first”, “second”, etc. may be used in various embodiments to modify an element, component, step, operation, etc., such as, for example, a “first decoding” and a “second decoding”. Use of such terms does not imply an ordering to the modified operations unless specifically required. So, in this example, the first decoding need not be performed before the second decoding, and may occur, for example, before, during, or in an overlapping time period with the second decoding.

[0215] Various numeric values may be used in the present application, for example. The specific values are for example purposes and the aspects described are not limited to these specific values.

[0216] Embodiments described herein may be carried out by computer software implemented by a processor or other hardware, or by a combination of hardware and software. As a non-limiting example, the embodiments can be implemented by one or more integrated circuits. The processor can be of any type appropriate to the technical environment and can encompass one or more of microprocessors, general purpose computers, special purpose computers, and processors based on a multi-core architecture, as non-limiting examples.

[0217] Various implementations involve decoding. “Decoding”, as used in this application, can encompass all or part of the processes performed, for example, on a received encoded sequence in order to produce a final output suitable for display. In various embodiments, such processes include one or more of the processes typically performed by a decoder, for example, entropy decoding, inverse quantization, inverse transformation, and differential decoding. In various embodiments, such processes also, or alternatively, include processes performed by a decoder of various implementations described in this application, for example, extracting a picture from a tiled (packed) picture, determining an upsampling filter to use and then upsampling a picture, and flipping a picture back to its intended orientation.

[0218] As further examples, in one embodiment “decoding” refers only to entropy decoding, in another embodiment “decoding” refers only to differential decoding, and in another embodiment “decoding” refers to a combination of entropy decoding and differential decoding. Whether the phrase “decoding process” is intended to refer specifically to a subset of operations or generally to the broader decoding process will be clear based on the context of the specific descriptions.

[0219] Various implementations involve encoding. In an analogous way to the above discussion about “decoding”, “encoding” as used in this application can encompass all or part of the processes performed, for example, on an input video sequence in order to produce an encoded bitstream. In various embodiments, such processes include one or more of the processes typically performed by an encoder, for example, partitioning, differential encoding, transformation, quantization, and entropy encoding. In various embodiments, such processes also, or alternatively, include processes performed by an encoder of various implementations described in this application.

[0220] As further examples, in one embodiment “encoding” refers only to entropy encoding, in another embodiment “encoding” refers only to differential encoding, and in another embodiment “encoding” refers to a combination of differential encoding and entropy encoding. Whether the phrase “encoding process” is intended to refer specifically to a subset of operations or generally to the broader encoding process will be clear based on the context of the specific descriptions.

[0221] When a figure is presented as a flow diagram, it should be understood that it also provides a block diagram of a corresponding apparatus. Similarly, when a figure is presented as a block diagram, it should be understood that it also provides a flow diagram of a corresponding method/process.

[0222] Various embodiments refer to rate distortion optimization. In particular, during the encoding process, the balance or trade-off between the rate and distortion is usually considered, often given the constraints of computational complexity. The rate distortion optimization is usually formulated as minimizing a rate distortion function, which is a weighted sum of the rate and of the distortion. There are different approaches to solve the rate distortion optimization problem. For example, the approaches may be based on an extensive testing of all encoding options, including all considered modes or coding parameters values, with a complete evaluation of their coding cost and related distortion of the reconstructed signal after coding and decoding. Faster approaches may also be used, to save encoding complexity, in particular with computation of an approximated distortion based on the prediction or the prediction residual signal, not the reconstructed one. A mix of these two approaches can also be used, such as by using an approximated distortion for only some of the possible encoding options, and a complete distortion for other encoding options. Other approaches only evaluate a subset of the possible encoding options. More generally, many approaches employ any of a variety of techniques to perform the optimization, but the optimization is not necessarily a complete evaluation of both the coding cost and related distortion.

[0223] The implementations and aspects described herein can be implemented in, for example, a method or a process, an apparatus, a software program, a data stream, or a signal. Even if only discussed in the context of a single form of implementation (for example, discussed only as a method), the implementation of features discussed can also be implemented in other forms (for example, an apparatus or program). An apparatus can be implemented in, for example, appropriate hardware, software, and firmware. The methods can be implemented in, for example, a processor, which refers to processing devices in general, including, for example, a computer, a microprocessor, an integrated circuit, or a programmable logic device. Processors also include communication devices, such as, for example, computers, cell phones, portable/personal digital assistants (“PDAs”), and other devices that facilitate communication of information between end-users.

[0224] Reference to “one embodiment” or “an embodiment” or “one implementation” or “an implementation”, as well as other variations thereof, means that a particular feature, structure, characteristic, and so forth described in connection with the embodiment is included in at least one embodiment. Thus, the appearances of the phrase “in one embodiment” or “in an embodiment” or “in one implementation” or “in an implementation”, as well any other variations, appearing in various places throughout this application are not necessarily all referring to the same embodiment.

[0225] Additionally, this application may refer to “determining” various pieces of information. Determining the information can include one or more of, for example, estimating the information, calculating the information, predicting the information, or retrieving the information from memory.

[0226] Further, this application may refer to “accessing” various pieces of information. Accessing the information can include one or more of, for example, receiving the information, retrieving the information (for example, from memory), storing the information, moving the information, copying the information, calculating the information, determining the information, predicting the information, or estimating the information. [0227] Additionally, this application may refer to “receiving” various pieces of information. Receiving is, as with “accessing”, intended to be a broad term. Receiving the information can include one or more of, for example, accessing the information, or retrieving the information (for example, from memory). Further, “receiving” is typically involved, in one way or another, during operations such as, for example, storing the information, processing the information, transmitting the information, moving the information, copying the information, erasing the information, calculating the information, determining the information, predicting the information, or estimating the information.

[0228] It is to be appreciated that the use of any of the following ”, “and/or”, and “at least one of”, for example, in the cases of “A/B”, “A and/or B” and “at least one of A and B”, is intended to encompass the selection of the first listed option (A) only, or the selection of the second listed option (B) only, or the selection of both options (A and B). As a further example, in the cases of “A, B, and/or C” and “at least one of A, B, and C”, such phrasing is intended to encompass the selection of the first listed option (A) only, or the selection of the second listed option (B) only, or the selection of the third listed option (C) only, or the selection of the first and the second listed options (A and B) only, or the selection of the first and third listed options (A and C) only, or the selection of the second and third listed options (B and C) only, or the selection of all three options (A and B and C). This may be extended for as many items as are listed.

[0229] Also, as used herein, the word “signal” refers to, among other things, indicating something to a corresponding decoder. For example, in certain embodiments the encoder signals a particular one of a plurality of parameters for region-based filter parameter selection for de-artifact filtering. In this way, in an embodiment the same parameter is used at both the encoder side and the decoder side. Thus, for example, an encoder can transmit (explicit signaling) a particular parameter to the decoder so that the decoder can use the same particular parameter. Conversely, if the decoder already has the particular parameter as well as others, then signaling can be used without transmitting (implicit signaling) to simply allow the decoder to know and select the particular parameter. By avoiding transmission of any actual functions, a bit savings is realized in various embodiments. It is to be appreciated that signaling can be accomplished in a variety of ways. For example, one or more syntax elements, flags, and so forth are used to signal information to a corresponding decoder in various embodiments. While the preceding relates to the verb form of the word “signal”, the word “signal” can also be used herein as a noun.

[0230] Implementations can produce a variety of signals formatted to carry information that can be, for example, stored or transmitted. The information can include, for example, instructions for performing a method, or data produced by one of the described implementations. For example, a signal can be formatted to carry the bitstream of a described embodiment. Such a signal can be formatted, for example, as an electromagnetic wave (for example, using a radio frequency portion of spectrum) or as a baseband signal. The formatting can include, for example, encoding a data stream and modulating a carrier with the encoded data stream. The information that the signal carries can be, for example, analog or digital information. The signal can be transmitted over a variety of different wired or wireless links, as is known. The signal can be stored on a processor-readable medium.

[0231] We describe a number of embodiments. Features of these embodiments can be provided alone or in any combination, across various claim categories and types. Further, embodiments can include one or more of the following features, devices, or aspects, alone or in any combination, across various claim categories and types:

• Adapting residues at an encoder according to any of the embodiments discussed.

• A bitstream or signal that includes one or more of the described syntax elements, or variations thereof.

• A bitstream or signal that includes syntax conveying information generated according to any of the embodiments described.

• Inserting in the signaling syntax elements that enable the decoder to adapt residues in a manner corresponding to that used by an encoder.

• Creating and/or transmitting and/or receiving and/or decoding a bitstream or signal that includes one or more of the described syntax elements, or variations thereof.

• Creating and/or transmitting and/or receiving and/or decoding according to any of the embodiments described.

• A method, process, apparatus, medium storing instructions, medium storing data, or signal according to any of the embodiments described.

• A TV, set-top box, cell phone, tablet, or other electronic device that performs adaptation of filter parameters according to any of the embodiments described.

• A TV, set-top box, cell phone, tablet, or other electronic device that performs adaptation of filter parameters according to any of the embodiments described, and that displays (e.g. using a monitor, screen, or other type of display) a resulting image. • A TV, set-top box, cell phone, tablet, or other electronic device that selects (e.g. using a tuner) a channel to receive a signal including an encoded image, and performs adaptation of filter parameters according to any of the embodiments described.

• A TV, set-top box, cell phone, tablet, or other electronic device that receives (e.g. using an antenna) a signal over the air that includes an encoded image, and performs adaptation of filter parameters according to any of the embodiments described.

[0232] Note that various hardware elements of one or more of the described embodiments are referred to as “modules” that carry out (i.e., perform, execute, and the like) various functions that are described herein in connection with the respective modules. As used herein, a module includes hardware (e.g., one or more processors, one or more microprocessors, one or more microcontrollers, one or more microchips, one or more application-specific integrated circuits (ASICs), one or more field programmable gate arrays (FPGAs), one or more memory devices) deemed suitable by those of skill in the relevant art for a given implementation. Each described module may also include instructions executable for carrying out the one or more functions described as being carried out by the respective module, and it is noted that those instructions could take the form of or include hardware (i.e., hardwired) instructions, firmware instructions, software instructions, and/or the like, and may be stored in any suitable non-transitory computer-readable medium or media, such as commonly referred to as RAM, ROM, etc.

[0233] Although features and elements are described above in particular combinations, one of ordinary skill in the art will appreciate that each feature or element can be used alone or in any combination with the other features and elements. In addition, the methods described herein may be implemented in a computer program, software, or firmware incorporated in a computer-readable medium for execution by a computer or processor. Examples of computer-readable storage media include, but are not limited to, a read only memory (ROM), a random access memory (RAM), a register, cache memory, semiconductor memory devices, magnetic media such as internal hard disks and removable disks, magneto-optical media, and optical media such as CD-ROM disks, and digital versatile disks (DVDs). A processor in association with software may be used to implement a radio frequency transceiver for use in a WTRU, UE, terminal, base station, RNC, or any host computer.

Claims

1. A method comprising: obtaining a previously decoded point cloud frame as a reference point cloud frame; obtaining a motion feature that describes a motion between the reference point cloud frame and a current point cloud frame; determining a predictor feature map based on the reference point cloud frame and the motion feature; obtaining a current feature map that represents the current point cloud frame given the predictor feature map as a condition; and reconstructing the current point cloud frame based on the current feature map and using the predictor feature map as a condition.

2. The method of claim 1 , wherein obtaining the motion feature that describes motion between the reference point cloud frame and the current point cloud frame comprises: performing motion analysis to generate a motion feature map using the reference point cloud frame and the current point cloud frame as inputs; and entropy encoding the motion feature map to generate the motion feature.

3. The method of claim 1 , wherein obtaining the motion feature that describes motion between the reference point cloud frame and the current point cloud frame comprises: performing a feature extraction on the reference point cloud frame to generate a first feature map; performing a feature extraction on the current point cloud frame to generate a second feature map; fusing the first and second feature maps to generate a fused feature map; and performing a feature aggregation on the fused feature map to generate the motion feature.

4. The method of claim 3, wherein the reference point cloud frame and the current point cloud frame are voxel-based representations, and wherein performing the feature extraction on the reference point cloud frame comprises: passing the reference point cloud frame through one or more multi-layer perceptron (MLP) blocks; and passing an output of the one or more MLP blocks through one or more convolutional layers to generate the first feature map, and wherein performing the feature extraction on the current point cloud frame comprises: passing the current point cloud frame through one or more multi-layer perceptron (MLP) blocks; and passing an output of the one or more MLP blocks through one or more convolutional layers to generate the second feature map.

5. The method of claim 3, wherein the reference point cloud frame and the current point cloud frame are point-based representations, and wherein performing the feature extraction on the reference point cloud frame comprises: performing a block partition on the reference point cloud frame; and performing a blockwise feature extraction on the block partitioned reference point cloud frame to generate the first feature map, and wherein performing the feature extraction on the current point cloud frame comprises: performing a block partition on the current point cloud frame; and performing a blockwise feature extraction on the block partitioned current point cloud frame to generate the second feature map.

6. The method of any one of claims 1-5, wherein obtaining the motion feature comprises performing motion analysis training.

7. The method of any one of claims 1-6, wherein determining the predictor feature map based on the reference point cloud frame and the motion feature comprises: performing a feature extraction on the reference point cloud frame to generate a first feature map; concatenating the first feature map with the motion feature; passing the concatenated first feature map through one or more multi-layer perceptron (MLP) blocks; and passing an output of the one or more MLP blocks through one or more convolutional layers to generate the predictor feature map.

8. The method of any one of claims 1-7, wherein performing the feature extraction on the reference point cloud frame comprises performing a point synthesis.

9. The method of any one of claims 1-8, wherein performing the feature extraction on the current point cloud frame comprises performing a point synthesis.

10. An apparatus comprising: a processor; and a non-transitory computer-readable medium storing instructions operative, when executed by the processor, to cause the apparatus to perform the method of any one of claims 1 through 9.

11. A method comprising: obtaining a previously encoded point cloud frame as a reference point cloud frame; obtaining a motion feature that describes motion between the reference point cloud frame and a current point cloud frame; determining a predictor feature map based on the reference point cloud frame and the motion feature; determining a current feature map that represents the current point cloud frame given the predictor feature map as a condition; and encoding the current feature map into a bitstream using the predictor feature map as a condition.

12. The method of claim 11 , wherein obtaining the motion feature that describes motion between the reference point cloud frame and the current point cloud frame comprises: performing motion analysis to generate a motion feature map using the reference point cloud frame and the current point cloud frame as inputs; and entropy encoding the motion feature map to generate the motion feature.

13. The method of claim 12, wherein obtaining the motion feature that describes motion between the reference point cloud frame and the current point cloud frame comprises: performing a feature extraction on the reference point cloud frame to generate a first feature map; performing a feature extraction on the current point cloud frame to generate a second feature map; fusing the first and second feature maps to generate a fused feature map; and performing a feature aggregation on the fused feature map to generate the motion feature.

14. The method of claim 13, wherein the reference point cloud frame and the current point cloud frame are voxel-based representations, and wherein performing the feature extraction on the reference point cloud frame comprises: passing the reference point cloud frame through one or more multi-layer perceptron (MLP) blocks; and passing an output of the one or more MLP blocks through one or more convolutional layers to generate the first feature map, and wherein performing the feature extraction on the current point cloud frame comprises: passing the current point cloud frame through one or more multi-layer perceptron (MLP) blocks; and passing an output of the one or more MLP blocks through one or more convolutional layers to generate the second feature map.

15. The method of claim 13, wherein the reference point cloud frame and the current point cloud frame are point-based representations, and wherein performing the feature extraction on the reference point cloud frame comprises: performing a block partition on the reference point cloud frame; and performing a blockwise feature extraction on the block partitioned reference point cloud frame to generate the first feature map, and wherein performing the feature extraction on the current point cloud frame comprises: performing a block partition on the current point cloud frame; and performing a blockwise feature extraction on the block partitioned current point cloud frame to generate the second feature map.

16. The method of any one of claims 11-15, wherein obtaining the motion feature comprises performing motion analysis training.

17. The method of any one of claims 11-16, wherein determining the predictor feature map based on the reference point cloud frame and the motion feature comprises: performing a feature extraction on the reference point cloud frame to generate a first feature map; concatenating the first feature map with the motion feature; passing the concatenated first feature map through one or more multi-layer perceptron (MLP) blocks; and passing an output of the one or more MLP blocks through one or more convolutional layers to generate the predictor feature map.

18. The method of any one of claims 11-17, wherein determining the current feature map comprises: performing a feature extraction on the current point cloud frame to generate a second feature map; concatenating the second feature map with the predictor feature map; passing the concatenated second feature map through one or more multi-layer perceptron (MLP) blocks; and passing an output of the one or more MLP blocks through one or more convolutional layers to generate the current feature map.

19. The method of any one of claims 11-18, wherein performing the feature extraction on at least one of the reference point cloud frame and the current point cloud frame comprises using an I nception-ResNet block.

20. An apparatus comprising: a processor; and a non-transitory computer-readable medium storing instructions operative, when executed by the processor, to cause the apparatus to perform the method of any one of claims 11 through 19.

21 . An apparatus comprising at least one processor configured to perform the method of any one of claims 1-9 and 11-19.

22. An apparatus comprising a computer-readable medium storing instructions for causing one or more processors to perform the method of any one of claims 1-9 and 11-19.

23. An apparatus comprising at least one processor and at least one non-transitory computer-readable medium storing instructions for causing the at least one processor to perform the method of any one of claims 1-9 and 11-19.

24. A signal including a bitstream generated according to any one of claims 1-9 and 11-19.