WO2025185992A1 - Avatar blendshape semantics representation - Google Patents

Abstract

Some embodiments of a method may include obtaining information corresponding to an avatar, wherein the information comprises a reference face mesh, an avatar face mesh, one or more morph targets and associated weights, and one or more facial semantics; re-topologizing the avatar face mesh to a topology of the reference face mesh; performing a deformation transfer process to transfer the morph targets with the facial semantics from the reference face mesh to the avatar face mesh; and linearly combining the transferred morph targets on the avatar face mesh to synthesize a facial expression.

Description

AVATAR BLENDSHAPE SEMANTICS REPRESENTATION CROSS-REFERENCE TO RELATED APPLICATIONS [0001] The present application claims benefit of European Patent Application No. EP24305326, entitled “AVATAR BLENDSHAPE SEMANTICS REPRESENTATION” and filed March 4, 2024, which is hereby incorporated by reference in its entirety. BACKGROUND [0002] The human face and body deform in different ways. While the body structure has rigid articulated bones rotating around joints, the face undergoes small non-rigid deformations incurred by the activation of facial muscles. Generally, different schemes are used for animating the body and face of an avatar. SUMMARY [0003] A first example method in accordance with some embodiments may include: obtaining information corresponding to an avatar, wherein the information includes an avatar face mesh, one or more morph targets and associated weights, and one or more facial semantics, and wherein the one or more facial semantics describe a deformation of the avatar face mesh; determining a set of generic morph targets and associated weights corresponding to the deformation of the avatar face mesh; and categorizing the set of generic morph target weights as a facial expression. [0004] In some embodiments of the first example method, determining the set of morph target weights corresponding to the deformation of the avatar face mesh includes: expressing the facial expression of the avatar face mesh using a linear combination of a subset of the one or more morph targets and associated weights; expressing each of the one or more morph targets as a weighted linear combination of generic morph targets; and expressing the avatar face mesh using a weighted linear combination of the generic morph targets. [0005] In some embodiments of the first example method, categorizing the set of morph target weights includes determining that at least one of the set of generic morph target weights is within a range associated with a category of the facial expression. [0006] In some embodiments of the first example method, the facial expression is described by the obtained information corresponding to the avatar. [0007] In some embodiments of the first example method, at least one of the one or more morph targets is a blendshape. [0008] In some embodiments of the first example method, the facial semantic is a Facial Action Coding System (FACS) blendshape semantic. [0009] 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. [0010] A second example method in accordance with some embodiments may include: obtaining information corresponding to an avatar, wherein the information includes an avatar face mesh, one or more morph targets and associated weights, and one or more facial semantics; re-topologizing the avatar face mesh to a topology of a reference face mesh; performing a deformation transfer process to transfer the morph targets with the facial semantics from the reference face mesh to the avatar face mesh; and linearly combining the transferred morph targets on the avatar face mesh to synthesize a facial expression. [0011] In some embodiments of the second example method, each of the facial semantics include a description of at least one of the one or more morph targets. [0012] In some embodiments of the second example method, each of the one or more morph targets represent a deformation of a face of the avatar, each of the facial semantics describe and correspond to one of the one or more morph targets, and each of the facial semantics include a decomposition and linear combination of two or more generic morph targets. [0013] In some embodiments of the second example method, the linear combination includes a linear combination of two or more FACS Action Unit blendshapes. [0014] In some embodiments of the second example method, re-topologizing the avatar face mesh to the topology of the reference face mesh includes: mapping each vertex of the reference face mesh to a location in the avatar face mesh; and replacing a location of each vertex of the reference face mesh with the mapped location in the avatar face mesh to warp the reference face mesh to a geometry of the avatar face mesh. [0015] In some embodiments of the second example method, performing the deformation transfer process includes: determining a set of geometric transforms, wherein each transform of the set of geometric transforms warps a triangle of the reference face mesh at rest to the triangle of the reference face mesh in which a corresponding morph target has been added; and applying the set of geometric transforms to the re- topologized avatar face mesh. [0016] In some embodiments of the second example method, linearly combining the transferred morph targets on the avatar face mesh includes: extracting a subset of the one or more morph targets corresponding to the facial expression; extracting a semantic description corresponding to at least one of the one or more morph targets; expressing each morph target of the subset of the one or more morph targets as a weighted linear combination of one or more generic morph targets; and performing a weighted linear combination of the weighted linear combinations of one or more generic morph targets of the subset. [0017] In some embodiments of the second example method, the facial expression is described by the obtained information corresponding to the avatar. [0018] In some embodiments of the second example method, at least one of the one or more morph targets is a blendshape. [0019] In some embodiments of the second example method, the facial semantic is a Facial Action Coding System (FACS) blendshape semantic. [0020] 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 the method of any one of the methods listed above. [0021] A third example method in accordance with some embodiments may include: obtaining information corresponding to an avatar, determining that the information includes node information corresponding to MPEG_node_avatar extension; determining that the node information includes semantics information corresponding to a facial_blendshape_semantics attribute; parsing the information corresponding to the avatar for target_indexes and FACS_targets attributes; and parsing the information corresponding to the avatar for AU_names and AU_weights FACS Action Unit descriptors in a FACS_targets array; [0022] A third 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. [0023] A fourth example method in accordance with some embodiments may include: obtaining information corresponding to an avatar, determining that the information includes node information corresponding to an avatar node; determining that the node information includes semantics information corresponding to morph target attributes of the avatar; parsing the information corresponding to a subset of the morph target attributes, wherein the subset represents facial deformations; and parsing the information corresponding to weights and names of generic morph targets describing semantics of the morph target attributes. [0024] A fourth 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 fifth example method in accordance with some embodiments may include: selecting a facial expression for use with an avatar; determining one or more morph targets and associated weights corresponding to the facial expression; generating information corresponding to the avatar, wherein the information includes an avatar face mesh, the one or more morph targets and the associated weights, and one or more facial semantics; communicating to a device the information corresponding to the avatar. [0026] In some embodiments of the fifth example method, at least one of the one or more morph targets is a blendshape. [0027] In some embodiments of the fifth example method, the facial semantic is a Facial Action Coding System (FACS) blendshape semantic. [0028] A fifth 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. [0029] A sixth example method in accordance with some embodiments may include: obtaining information corresponding to an avatar, wherein the information includes an avatar face mesh in a neutral pose, a description of semantics of each avatar blendshape as a linear combination of reference blendshapes of a reference blendshape model, and a weight of each avatar blendshape; re-topologizing the avatar face mesh in the neutral pose to a topology of a template face mesh with a predetermined topology; performing a deformation transfer process to transfer the reference blendshapes of the template face mesh with the predetermined topology to the retopologized avatar face mesh; and reconstructing the blendshapes of the avatar face mesh by linearly combining the transferred reference blendshapes on the retopologized avatar face mesh according to their semantic description. [0030] For some embodiments of the sixth example method, each of the reference blendshapes represents a deformation of a face of the avatar. [0031] For some embodiments of the sixth example method, the linear combination includes a linear combination of two or more FACS Action Unit blendshapes. [0032] For some embodiments of the sixth example method, re-topologizing the avatar face mesh in the neutral pose to the topology of the template face mesh includes: mapping each vertex of the template face mesh to a location in the avatar face mesh; and replacing a location of each vertex of the template face mesh with the mapped location in the avatar face mesh to warp the template face mesh to a geometry of the avatar face mesh. [0033] A sixth example apparatus in accordance with some embodiments may include: a processor; ann- 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. [0034] A seventh example apparatus in accordance with some embodiments may include at least one processor configured to perform the method of any one of the methods listed above. [0035] An eighth 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. [0036] A ninth 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. [0037] An example single in accordance with some embodiments may include information corresponding to an avatar, generated according to any one of the methods listed above. BRIEF DESCRIPTION OF THE DRAWINGS [0038] FIG.1A is a system diagram illustrating an example communications system according to some embodiments. [0039] FIG.1B is a system diagram illustrating an example wireless transmit/receive unit (WTRU) that may be used within the communications system illustrated in FIG.1A according to some embodiments. [0040] FIG.1C is a system diagram illustrating an example set of interfaces for a system according to some embodiments. [0041] FIG.2 is a schematic illustration showing example levels of detail for example avatar mesh models. [0042] FIG.3A is a schematic illustration showing an example reference head mesh according to some embodiments. [0043] FIG.3B is a schematic illustration showing an example mesh with deformation according to some embodiments. [0044] FIG.3C is a schematic illustration showing an example mesh with deformation according to some embodiments. [0045] FIG. 4 is a flowchart illustrating an example process for parsing of the “facial_blendshape_semantics” attribute of the “MPEG_node_avatar” extension according to some embodiments. [0046] FIG.5 is a flowchart illustrating an example process for generation of a facial expression in an avatar mesh according to some embodiments. [0047] FIG.6 is a flowchart illustrating an example process for recognition of an emotion expressed by an avatar according to some embodiments. [0048] FIG. 7 is a flowchart showing an example of synthesizing a facial expression on an avatar according to some embodiments. [0049] FIG.8 is a flowchart showing an example of categorizing a facial expression on an avatar according to some embodiments. [0050] FIG. 9 is a flowchart showing an example of parsing information corresponding to a facial expression on an avatar according to some embodiments. [0051] FIG.10 is a flowchart showing an example of generating information corresponding to a facial expression on an avatar according to some embodiments. [0052] 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 by way 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 [0053] 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. [0054] 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 CN 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 (IoT) 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. [0055] 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. [0056] 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. [0057] 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). [0058] 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). [0059] 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). [0060] 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). [0061] 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). [0062] 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, CDMA20001X, 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. [0063] 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.1A, 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. [0064] 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. [0065] 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. [0066] 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 cellular-based radio technology, and with the base station 114b, which may employ an IEEE 802 radio technology. [0067] FIG.1B is a system diagram illustrating an example WTRU 102. As shown in FIG.1B, 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. [0068] 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.1B 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. [0069] 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. [0070] Although the transmit/receive element 122 is depicted in FIG.1B 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. [0071] 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. [0072] 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). [0073] 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. [0074] 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. [0075] 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. [0076] 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)). [0077] Although the WTRU is described in FIGs.1A-1B 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. [0078] In representative embodiments, the other network 112 may be a WLAN. [0079] In view of FIGs.1A-1B, 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. [0080] 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. [0081] 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. [0082] FIG.1C 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. [0083] 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. [0084] 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. [0085] 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. [0086] 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 VVC (Versatile Video Coding, a new standard being developed by JVET, the Joint Video Experts Team). [0087] 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.1C, include composite video. [0088] 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, band-limiters, 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. [0089] 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. [0090] 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 Inter- IC (I2C) bus, wiring, and printed circuit boards. [0091] 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. [0092] 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. [0093] 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. [0094] 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. [0095] 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. [0096] 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. [0097] 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. Avatar Animation [0098] The representation of digital humans and their interaction with 3D virtual environments, as well as the animation of the facial expressions of avatars, which are based on blendshapes for some embodiments, are discussed below. [0099] The human face and body deform in different ways. While the body structure has rigid articulated bones rotating around joints, the face undergoes small non-rigid deformations incurred by the activation of facial muscles. As a result, two separate schemes may be used for animating the body and face of an avatar. [0100] The standard approach for animating an avatar body is to drive the avatar by the motion of a skeleton. The skeleton is a directed acyclic graph of joint nodes linked by bone edges. The degrees of freedom of a skeleton are: (1) the 3D positions of its joints, (2) the relative 3D rotations of each bone with respect to its parent bone in the graph, and (3) the absolute position of its root joint. Joints are often mapped to physical human body joints, such as an elbow, ankle, or wrist. The root joint of the graph is usually chosen to be the pelvis. [0101] FIG.2 is a schematic illustration showing example levels of detail for example avatar mesh models. The envelope of the avatar body is represented by a mesh. Example avatar mesh geometries are shown in FIG.2. FIG.2 shows topologies 200, 202, 204 of the avatar mesh reference models for the MPEG-I Scene Description standard, for various levels of detail (from left to right: high, medium and small). See [SD] Update of Annex H on Potential Improvement CDAM223090-14 document – Reference Avatar, MPEG Meeting #143, Document m63997 (July 2023) (“m63997”). [0102] The animation of the envelope mesh is controlled by the motion of the skeleton joints through a process known as skinning. The most popular approach to skinning is Linear Blend Skinning (LBS). In this approach, the position of each vertex of the avatar mesh in a pose of the skeleton during an animation – hereafter referred to as an “animation pose” – is computed as a geometric transformation of the same vertex in a known reference pose of the skeleton known as the ”binding pose”. The “pose” of the skeleton is a particular instance of relative joint positions and bone rotations that indicates or defines the posture of the avatar body. [0103] FIG.3A is a schematic illustration showing an example reference head mesh according to some embodiments. FIG.3B is a schematic illustration showing an example mesh with a deformation according to some embodiments. FIG.3C is a schematic illustration showing an example mesh with another deformation according to some embodiments. [0104] FIGs.3A-3C show a reference head mesh in a neutral expression 300 (FIG.3A) and two meshes 302, 304 (FIGs.3B and 3C) obtained each by adding a morph target deformation to the reference mesh. [0105] Morph targets, which are known as blendshapes, provide another way to animate an avatar mesh, and particularly to sculpt facial expressions. They are essentially 3D deformations with respect to the geometry of a reference head mesh and are represented by the 3D offsets to the positions of each vertex of the reference head mesh. Typically, the reference head mesh models the avatar with a neutral face expression that shows no emotion. Morph targets are provided in addition to the reference head mesh. Each morph target is associated with a scalar weight. The desired shape of the mesh is obtained by adding to the vertex positions of the reference head mesh a linear combination of the vertex offsets of several morph targets, weighted by their corresponding weights. Advantageously, morph targets are mapped to deformations of the neutral face geometry incurred by the activation of facial muscles. Combining these deformations provides a convenient way for artists to sculpt the shape of the face mesh so that the face mesh expresses a specific emotion. [0106] Morph targets model deformations of an avatar face mesh that represent facial expressions of an avatar. Action Units may model more elementary deformations of the avatar face mesh that are person- generic. Hence, decomposing a morph target as a linear combination of Action Units may provide a person- generic representation of a facial expression (e.g., the semantics of the facial expression). [0107] A facial expression is a combination of one or more morph targets. These one or more morph targets are a subset of all the morph targets provided in the avatar description (other morph targets may be used, e.g., to describe the animation of the avatar body). Each of the one or more morph targets in the subset is described as a weighted linear combination of generic (more elementary) morph targets (e.g., the FACS Action Units). Because these generic morph targets are person-generic, they provide semantics for each of the one or more morph targets in the subset. Hence, they provide semantics for the facial expression that is a linear combination of these one or more morph targets. The facial expression of the avatar is a linear combination of the one or more morph targets. Hence, facial expression is a linear combination of weighted linear combinations of generic morph targets. [0108] An avatar face mesh is the sum of the base mesh under a neutral expression and the weighted linear combination of morph targets (since morph targets are deformations of the base mesh). A facial expression is a deformation of the base mesh. [0109] For some embodiments, there are two sets of morph targets: (1) the subset of one or more morph targets defining the facial expression of an avatar, and (2) the generic (more elementary) morph targets (e.g., FACS Action Units) that define the semantics of the one or more morph targets. Avatars in the MPEG-I Scene Description Standard [0110] The specification Khronos glTF Specification for the Efficient Transmission and Loading of 3D Scenes and Models by Engines and Applications, KRONOS, Version 2.0, available at www<dot>khronos<dot>org/gltf (“glTF 2.0”) and the MPEG-I Scene Description (SD) specifications Draft Text of ISO/IEC 23090-142nd Edition Scene Description (July 2023) (“ISO/IEC 23090-142nd Edition”) and Text of ISO/IEC 23090-14 CDAM 2: Support for Haptics, Augmented Reality, Avatars, Interactivity, MPEG-I Audio, and Lighting (“ISO/IEC 23090-14 CDAM 2”) provide standardized descriptions for representing the basic geometry, texture and animation of an avatar. The glTF specification covers the description of the elements of the skinning model, in particular the graph of joints forming the skeleton and the skinning weights. The glTF specification also provides descriptors for a mesh and associated morph targets with corresponding weights. [0111] Further, amendment 2 of MPEG-I SD (See ISO/IEC 23090-14 CDAM 2 and Avril, Q., et al., [SD] Avatar Description and Mapping, MPEG Meeting #142, Document m63505 (April 2023) (“m63505“)) defines a specialization of a glTFnode for avatars through an MPEG_node_avatar extension. MPEG_node_avatar does not impose a specific avatar representation scheme for the geometry, texture, and animation of an avatar. Instead, a scheme can be specified as a Uniform Resource Name encoded in the mandatory type attribute of the extension, pointing to a description of a representation scheme. A reference scheme that may be used by default is provided in m63997. [0112] Besides an avatar representation scheme, the MPEG_node_avatar extension describes the semantics of body parts through an array of mapping instances that each map a part of the full avatar 3D mesh to a semantic label. Aside from this attribute, MPEG_node_avatar as understood does not standardize any semantic descriptions of avatar features. For instance, the deformation of the avatar face geometry corresponding to a smile may be described by appropriate values of the morph targets and associated weight attributes of the avatar mesh, but no means are provided for labeling this deformation as a smile in a way that is understood by all applications. [0113] Immersive communication platforms, in which users are represented using avatar proxies navigating in virtual environments, have to deal with a variety of avatar representations. Indeed, users want to create their avatar model using a 3D authoring tool and want to use the model on various platforms without re-designing a specific avatar model for each platform. [0114] Each avatar representation scheme comes with its own semantics. In particular, the semantics of morph targets used to represent facial expressions are likely to differ from one representation scheme to the next. Some representation schemes may map morph targets to a subset of the action units specified in the Facial Action Coding System (Ekman, P. and Friesen, W.V., Measuring Facial Movement, Environmental Psychology and Nonverbal Behavior, Vol.1, no.1, pp.56-75 (1976) (“Ekman”) and FACS Cheat Sheet, MELINDA OZEL, available at melindaozel<dot>com/facs-cheat-sheet/ (“FACS Cheat Sheet”)). Such action units correspond to the activations of specific facial muscles or groups of closely related facial muscles. However, each representation may choose a different subset. Other representations may associate morph targets with facial expressions corresponding to emotions, such as surprise, happiness, or fear. [0115] This variability of representation schemes creates a portability issue, because many of the features proposed by immersive communication platforms and applications are dependent on morph target semantics. [0116] In a first example, applications want to provide users with controls over the emotions expressed by their avatars, such as surprise, smile or fear. For instance, users may be given the possibility to make their avatar smile by pressing a “smile” button. To implement this functionality, applications may store pre- computed animations for each facial expression of each user avatar. However, this functionality requires transmitting, for each avatar, animations for each semantic facial expression, typically representing an emotion, which has to be rendered by the avatar. Transmitting semantic descriptors of the morph targets associated with the user avatar representation is more efficient both in terms of transmission bandwidth and memory storage requirements on the application side, while achieving the same functionality. Indeed, having semantic descriptors of the morph targets associated with the facial deformations of the avatar geometry allows the application to generate animations of the avatar expressing emotions on-the-fly instead of relying on predefined animations. For instance, if a morph target in an avatar representation is associated with the expression of surprise, surprise on the face of the avatar may be synthesized by setting the weight of the morph target to a non-zero value. If morph targets in the avatar representation correspond to the activation of facial muscles, then surprise may be synthesized by setting non-zero weights for the morph targets associated with the expression of surprise, specifically, the brow raiser and jaw drop muscles. [0117] In a second example, applications may want to automatically trigger facial expressions on the face of an avatar based on specific events. For instance, an application may make an avatar smile automatically when the avatar meets another avatar identified as a friend or may force an expression of pain on an avatar face when the avatar bumps against a wall or a piece of furniture in the virtual environment. Similar to the above use case, if an application does not have access to descriptors providing the semantics of the morph targets associated with the deformations of the avatar face geometry, the application must rely on pre-defined animations for rendering avatar emotions, incurring a much larger transmission bandwidth and memory footprint on the application side. [0118] In a third example, applications may want to automatically recognize emotions on avatars based on their facial expressions. This functionality may be used, for instance, to trigger interactions. An avatar smiling as the avatar passes another avatar may automatically trigger the start of a friendly conversation between the two characters. When an application detects anger or sadness on the face of an avatar, the application may want to automatically adapt the environment, for example, using soothing colors or music. E-learning applications may want to automatically detect surprise or lack of understanding on the faces of student avatars in order to provide more explanations on the concept that was just presented by a virtual teacher. To implement such a behavior, an application must be able to interpret the morph target or combination of morph targets deforming a face as the expression of a particular emotion. Hence, the description of the avatar may include semantic descriptors of the facial morph targets. Without these descriptors, the application may have difficulty inferring the emotions expressed by the avatar. [0119] These examples illustrate the benefits of enriching the description of an avatar that is transmitted to a platform by semantic descriptors of the facial morph targets. This application defines a representation of morph target semantics that allows the portability of the synthesis and recognition of the emotions expressed by an avatar across immersive communication platforms. [0120] For some embodiments to solve the aforementioned issue, the description of an avatar may be enriched with new attributes that describe the semantics of the morph targets used to deform the geometry of its face in order to express emotions. [0121] Specification of these new attributes, which is provided below, is compliant with the MPEG-I Scene Description format (See glTF 2.0; ISO/IEC 23090-142nd Edition; and ISO/IEC 23090-14 CDAM 2). However, its meaning and use is generic. These new attributes may be encoded in any other scene description format, such as XML or USD. [0122] For the sake of universality, the description of the morph target semantics builds on the pseudo- anatomical Facial Action Coding System (FACS) proposed by Ekman (See also FACS Cheat Sheet). In this system, facial expressions are modelled as a superimposition of elementary deformations associated with facial muscles or groups of closely related facial muscles. These elementary deformations, examples of which are “inner brow raiser” or “lip corner puller“, are referred to as “Action Units”. However, any other person-generic model for representing facial expressions may be used instead for some embodiments. [0123] Each morph target representing the deformation of the face mesh at rest (or under a neutral expression), involved in the expression of an emotion, is described using a weighted linear combination of Actions Units. The semantics of morph targets in the avatar representation associated with a deformation of the face geometry is described as an array of Action Unit labels and a corresponding array of scalar weights in the range [0.0, 1.0]. The two arrays must have the same dimension. The i^th element of the weights array applies to the i^th label in the Action Unit label array. For each Action Unit label, a weight of 0.0 indicates the absence of deformation associated with the Action Unit. A weight of 1.0 indicates the maximal deformation associated with the Action Unit. Weights between 0.0 and 1.0 indicate intermediate deformations associated with the Action Unit. [0124] This representation of morph targets semantics for facial expression has two major advantages. First, since the description relies on an anatomical model, the description may be unambiguously understood by all applications. Second, the description is generic because virtually any physically plausible deformation of a human face may be represented as a weighted combination of FACS Action Units. Enrichment of the Avatar Description in MPEG-I Scene Description [0125] In MPEG-I Scene Description (SD), an avatar is described by the “MPEG_node_avatar” extension to a “node” object representing the avatar. The “MPEG_node_avatar” may be enriched with attributes that define the semantics of the morph targets used to model the deformations of the avatar face mesh geometry representing facial expressions. Herein, in accordance with some embodiments, the term “blendshape” is used interchangeably with the term “morph target”. [0126] The node that “MPEG_node_avatar” extends is assumed to contain a mesh attribute that models the geometry of the avatar face, possibly with other parts of the avatar body, or the whole avatar body. In the context of this invention, it is further assumed that the description of the avatar mesh contains at least one morph target representing the deformation of the face geometry associated with a facial expression. Such a morph target may be provided in the scene description as an element of a ”targets” array attribute of at least one mesh primitive. [0127] Table 1 shows a new “facial_blendshape_semantics” attribute of the “MPEG_node_avatar” extension. The semantics of facial blendshapes are described by means of a new “facial_blendshape_semantics” attribute that is added to the “MPEG_node_avatar” extension, which is shown in Table 1. Some embodiments may use this attribute. Name Type Required Description Semantics of the morph targets associated with facial_blendshape_semantics Facial_Blendshape_Semantics No the facial expressions of the avatar Table 1. [0128] The “facial_blendshape_semantics” attribute is an instance of a new “Facial_Blendshape_Semantics” type, whose properties are shown in Table 2. The attribute “facial_blendshape_semantics” is used only for application features that require the knowledge of the facial blendshape semantics and may be ignored by applications that do not use such features. If the “facial_blendshape_semantics” attribute is not provided in a scene description, applications that require this attribute for implementing some of their features may deactivate these features. [0129] The ”Facial_Blendshape_Semantics” type contains the attributes listed in Table 2. Within the ”targets” arrays of morph targets for the avatar mesh, the ”target_indexes” array identifies the facial blendshapes whose semantics is provided in the description. The semantics of each such blendshape is described by an instance of the “FACS_Target” type in the “FACS_targets” array. The ”target_indexes” and “FACS_targets” arrays have the same dimensions, the i^th element of “FACS_targets” provides the semantic description of the blendshape pointed to by the i^th element of ”target_indexes”. Table 2 lists descriptions of the “Facial_Blendshape_Semantics” type properties. Name Type Required Description Indexes in the “targets” array of the mesh primitive target_indexes integer[1-*] Yes representing the geometry of the avatar face of the morph targets representing facial expressions FACS-based descriptions of the semantics of the morph FACS_targets FACS_Target[1-*] Yes targets with indexes in “target_indexes” Table 2. [0130] The semantic description of a facial blendshape is encapsulated in the “FACS_Target” type, whose properties are described in Table 3. In the FACS model, each Action Unit is associated with a deformation of the face geometry that may be modeled as a morph target on the mesh of an avatar face. The Action Unit names and numbers, which are listed in Ekman, are reproduced in Table 4 for completeness. Each facial blendshape may be described by a weighted linear combination of FACS Action Unit morph targets that produces the same deformation as the particular blendshape. The attributes of the “FACS_Target” type correspond to the ”AU_names” array of Action Unit labels. The corresponding weights, ”AU_weights”, may be used with the weighted linear combination. ”AU_names” and ”AU_weights” must have the same dimensions. The i^th element of “AU_weights” is the weight associated with the Action Unit deformation identified by the i^th label in the ”AU_names” array. For a given facial blendshape, the weights of the FACS Action Units correspond to the level of activation of the corresponding facial muscles and are not constrained to sum up to 1. Name Type Required Description Array of names of FACS Action Units whose linear combination AU_names string[1-*] Yes matches the current morph target instance Array of weights in [0.0,1.0] of the linear combination of FACS AU_weights number[1-*] Yes Action Units that matches the current morph target instance Table 3. [0131] Based on reference material available from FACS books or resources found on the web, such as FACS Cheat Sheet, a framework or application that consumes the ”Facial_Blendshape_Semantics” description will be able to map each of the Action Units listed in Table 4 to a deformation of some reference face mesh. Using mesh correspondence and deformation transfer methods, as described in Sumner, R.W. and Popovic, J., Deformation Transfer for Triangle Meshes, 23:3 ACM TRANS. ON GRAPHICS 399-405 (Aug. 2004) (“Sumner”), for example, the Action Unit deformations may be transferred from the reference face mesh to the face region of the user-provided avatar mesh. Thus, for each FACS Action Unit, the application will be able to generate a corresponding morph target on the user-provided avatar face mesh. [0132] As a result, when receiving the semantic description of a facial expression on the mesh of a user- defined avatar, as a ”Facial_Blendshape_Semantics” instance, the application may translate the Action Unit labels and weights encoded in this instance into a deformation of the user-defined mesh that matches the semantics of the facial expression. [0133] Table 1 describes a set of FACS facial blendshape action units (See Ekman).

Action _{Action Unit Name} ^Action Action Unit Name Unit ID Unit ID 1 Inner Brow Raiser 25 Lips Part 2 Outer Brow Raiser 26 Jaw Drop 4 Brow Lowerer 27 Mouth Stretch 5 Upper Lid Raiser 28 Lip Suck 6 Cheek Raiser 29 Jaw Thrust 7 Lid Tightener 30 Jaw Sideways 9 Nose Wrinkler 31 Jaw Clencher 10 Upper Lid Raiser 32 Lip Bite 11 Nasolabial Fold Deepener 33 Cheek Blow 12 Lip Corner Puller 34 Cheek Puff 13 Cheek Puffer 35 Cheek Suck 14 Dimpler 36 Tongue Bulge 15 Lip Corner Depressor 37 Lip Wipe 16 Lower Lip Depresssor 38 Nostril Dilator 17 Chin Raiser 39 Nostril Compressor 18 Lip Puckerer 41 Lid Droop 19 Tongue Out 42 Slit 20 Lip Stretcher 43 Eyes Closed 21 Neck Tightener 44 Squint 22 Lip Funneler 45 Blink 23 Lip Tightener 46 Wink 24 Lip Pressor Table 4. Example MPEG-I SD Description [0134] The example scene description in MPEG-I SD format below describes a scene with a single root node named “user_avatar_node” in the “nodes” array. [0135] This “user_avatar_node” node describes an avatar. Accordingly, its description is enriched by a “MPEG_node_avatar” extension. It holds a reference to a “mesh” object that describes the geometry and texture of the avatar representation. This mesh object named “user_avatar_mesh” is the first element in the “meshes” array. Its description includes 4 morph targets with corresponding weights. The morph targets are referenced by accessors indexed 3 to 6. For clarity, the buffers and buffer views pointed to by the accessors are not included in the description. [0136] The “facial_blendshape_semantics” attribute of “MPEG_node_avatar” is an array that provides the semantic descriptions of a subset of the morph targets. The “target_indexes” attribute specifies that semantic descriptions are provided for morph targets indexed 0, 1 and 3 among the 4 morph targets defined for the avatar mesh primitives in the example scene description shown in the code listing appearing below. These semantic descriptions are provided in the “FACS_targets” array attribute, each as an array of FACS Action Unit names and corresponding morph target weights. For instance, the 4^th morph target in the avatar mesh, corresponding to index 3 in the “targets” array and to the last of the three morph targets described in the “FACS_targets” array, combines the activation of the “cheek raiser” muscle with an activation level of 0.6 and the “lip corner puller” muscle with an activation of 0.9. The “cheek raiser” and the “lip corner puller” are the main facial muscles involved in smiling. Hence, the 4^th morph target represents a smile. { "scene": 0, "scenes": [ { "nodes": [0] } ], "meshes": [ { "name": "user_avatar_mesh", "primitives": [ { "attributes": { "POSITION": 0, "TEXCOORD_0": 1 }, "indices": 2, "targets": [ { "POSITION": 3 }, { "POSITION": 4 }, { "POSITION": 5 }, { "POSITION": 6 } ] } ], "weights": [0.3, 0.5, 0.1, 0.8], } ], "nodes": [ { "name": "user_avatar_node", "mesh": 0, "extensions": { "MPEG_node_avatar": { "isAvatar": true, "mappings": [], "type": “urn:my_avatar_type” , "facial_blendshape_semantics": { "target_indexes": [0, 1, 3], "FACS_targets": [ { "AU_names": [“Brow Lowerer”, “Cheek Raiser”], "AU_weights": [0.7, 0.5] }, { "AU_names": [“Lip Tightener”, “Dimpler”, “Chin Raiser”], "AU_weights": [0.2, 0.8, 0.7] }, { "AU_names": [“Cheek Raiser”, “Lip Corner Puller”], "AU_weights": [0.6, 0.9] } ] } } } } ], "extensionsUsed": [ "MPEG_node_avatar” ], "extensionsRequired": [ "MPEG_node_avatar" ], "asset": { "version”: ["2.0"] } } Parsing of the “facial_blendshape_semantics” Attribute [0137] FIG. 4 is a flowchart illustrating an example process for parsing of the “facial_blendshape_semantics” attribute of the “MPEG_node_avatar” extension according to some embodiments. Processing Model [0138] At runtime, an application processes the scene description that contains an avatar “node” instance including an “MPEG_node_avatar” extension by parsing 402 an MPEG-I SD “nodes” array and determining 404 if a node with the “MPEG_node_avatar” extension is found. If a node with the “MPEG_node_avatar” extension is found, the example process 400 determines 406 if the “MPEG_node_avatar” extension has a “facial_blendshape_semantics” attribute. Otherwise, the example process 400 exits. [0139] If the “MPEG_node_avatar” extension has a “facial_blendshape_semantics” attribute, then the example process 400 parses 408 the “target_indexes” and “FACS_targets” attributes and parses 410 the “AU_names” and “AU_weights” PCSA Action Units descriptors in the FACS_targets array. Otherwise, the example process 400 exits. [0140] The avatar “node” holds a reference to a “mesh” instance, in which the description of the face geometry corresponds to a neutral expression. Some or all of the elements of the “primitives” array of the “mesh” instance hold a “targets” array attribute describing the morph targets for an avatar face mesh. Some of these morph targets represent facial blendshapes. The corresponding morph target weights are provided in the “weights” attribute of either the avatar “node” instance or the “mesh” instance representing the geometry of the avatar. [0141] Topology and geometry in relation to the mesh of an avatar are described below. The topology of a mesh specifies how the surface of the mesh is sampled with vertices and how the vertices are connected with edges. In avatar meshes with identical topologies, the positions of the vertices on the surface of the meshes with respect to semantic anchors on the surface of a body – such the nose tip or the outer corner of the right eye – should be the same. The geometry of a mesh specifies its shape. For a given topology, the geometry of a mesh is specified by the positions of its vertices. A morph target corresponds to a change in the geometry of a mesh, while the mesh topology remains unchanged. [0142] The application that processes the scene description holds a reference face mesh ^^^{^^^} with a predefined topology and geometry. The set of blendshapes ^^^^^ ^{^^,^^^} ^ ^ representing all FACS Action Units defined in the proposed extension (see Table 4) are available in the application as deformations of this reference face mesh. Each such blendshape provides a geometrical model for a FACS Action Unit. Since the deformations of the face geometry associated with plausible facial expressions may be represented as linear combinations of FACS Action Unit blendshapes, the set of Action Unit blendshapes ^^^^^ ^{^^,^^^} ^ ^ provide a geometrical model for the semantics of facial expressions on the reference face mesh Thus, according to some embodiments, the blendshapes (or morph targets for some embodiments) provided in the description of an avatar mesh may be registered to this set of blendshapes. [0143] For some embodiments, the reference mesh and the user avatar face mesh are assumed to be triangular meshes. Other mesh representations may be used, such as mesh faces represented using quads. [0144] Processing models associated with the two use cases: (i) generation of an expression with a given semantics on the face of the avatar, and (ii) recognition of a facial expression from the description of the avatar geometry are described below. Generating a Facial Expression in an Avatar Mesh [0145] FIG.5 is a flowchart illustrating an example process for generation of a facial expression in an avatar mesh according to some embodiments. FIG.5 shows parsing and processing of the scene description elements to generate a facial expression on a user-provided avatar face mesh. Some embodiments may generate a facial expression using predefined semantics on the mesh of the avatar. [0146] In block 510, the application retrieves its reference face mesh ^^^{^^^} under a neutral expression, as well as the set of blendshapes ^^^^^ ^{^^,^^^} ^ ^ that represent the deformations of ^^^{^^^} resulting from all the FACS Action Units activations. These blendshapes are typically manually sculpted by artists offline. They provide a geometrical reference for the semantics of facial blendshapes, since each blendshape is associated with the maximal activation of a facial muscle or a group of facial muscles. [0147] In block 520, the application parses the scene description to extract elements used for synthesis of a facial expression of the user avatar. A first such element is a description of the user avatar mesh M at rest (under a neutral expression). A second such element is the set of blendshapes ^^^^^_^ ^ெ^ associated to this mesh, encoded as the “targets” attribute of the mesh primitives. A third such element is the set of weights ^^^_^^ corresponding to the mesh blendshapes ^^^^^_^ ^ெ^. A fourth such element is the description of the semantics of a subset of the above blendshapes involved in the synthesis of the facial expression of the avatar face mesh. This description is encoded in the “facial_blendshape_semantics” attribute of the “MPEG_node_avatar” extension of the node representing the avatar. This description is provided for each blendshape ^^^^^_^ ^ெ^ as a mapping to a linearly weighted combination of FACS Action Unit blendshapes ^^^^^_^ ^{^} ,^{^} ^ ^ with corresponding weights ^^^_^ ^{^} ,^{^} ^ ^ that quantify the activations of facial muscles. [0148] In block 530, the user avatar face mesh M and the reference face mesh ^^^{^^^} for the application is computed. In this process, each vertex of the reference face mesh ^^^{^^^} is mapped to a location on the surface of M. By replacing the positions of ^^^{^^^} vertices with computed corresponding locations on the surface of M, the reference mesh may be warped to the geometry of the avatar face mesh, while retaining its original topology. Stated differently, the result of this warp is a re- topologization of the avatar face mesh M to the topology of the reference mesh ^^^{^^^}. This re-topologized mesh is referred to hereafter as ^^^{^^௧^^^}. Several methods for computing correspondence between meshes may be used, such as the method described in Sumner. [0149] In block 540, a deformation transfer is applied to the re-topologized avatar face mesh ^^^{^^௧^^^} output of block 530 to transfer the FACS Action Unit blendshapes for the reference mesh retrieved in block 510 to this re-topologized avatar face mesh. The deformation transfer adapts the FACS Action Unit blendshapes ^^^^^ ^{^^,^^^} ^ ^ defined for the morphology of the reference face mesh to the morphology of the user avatar face mesh. The deformation transfer may be performed in two sub-steps. In a first sub-step, for each FACS Action Unit, indexed by k, the geometric transforms are computed. These geometric transforms warp the triangles of the reference mesh at rest (^^^{^^^}) to the same triangles of the reference mesh in which the corrsponding Action Unit blendshape ^^^^ ^{^^,^^^} ^ has been added. An advantage of a FACS model for some embodiments is that a FACS model is person-generic. An FACS model captures facial muscle activations. Since human faces have the same facial muscles, the semantics of the FACS model are the same for all characters. The FACS semantics shown in block 540 are the same as the blendshape semantics shown in block 520. [0150] In a second sub-step, these geometric transforms are applied to the triangles of the re-topologized mesh ^^^{^^௧^^^} output of block 530, while ensuring spatial continuity of the transformed triangles to obtain a regular mesh. The output of this second sub-step is a set of meshes {^^_^ ^{^^}} representing, for each FACS Action Unit, the deformation of the considered FACS Action Unit on the facial morphology of the re- topologized avatar face mesh. Several methods for computing deformation transfer between meshes may be used, such as the method described in Sumner. [0151] The output of the deformation transfer process is a set of meshes ^^^_^ ^{^^}^, each with the topology of the reference mesh and the geometry of the avatar mesh that represents of the face. Each ^^_^ ^{^^} represents the deformed version of the avatar face geometry under the activation of a FACS Action Unit. The set covers all the FACS Action Units listed in Table 4. The output of block 540 is obtained by subtracting the 3D positions of the re-topologized avatar face mesh ^^^{^^௧^^^} output of block 530 from the 3D positions of the vertices of each of the ^^_^ ^{^^} output by the deformation transfer process of block 540. _{Each ^^^^ ^^,^^௧^^^ ^ ≝ ^^^} ^{^^} െ^^^{^^௧^^^} quantity provides the morph target associated with the deformations of the FACS Action Unit i for the re-topologized avatar face mesh. [0152] In block 550, a subset of the morph targets ^^^ _{^^ ^^௧^^^ ^ െ ^^ ^ determined in block 540 are} linearly combined to synthesize the facial expression of the avatar mesh corresponding to the semantics specified in the “facial_blendshape_semantics” attribute of the scene description. The synthesis proceeds in several sub-steps. [0153] In a first sub-step, the subset of blendshapes ^^^^^_^ ^ெ} associated to the avatar face mesh M that are used to generate the facial expression of M are extracted from the “facial_blendshape_semantics.target_indexes” attribute of the “MPEG_node_avatar” extension, retrieved in block 520. [0154] In a second sub-step, the semantic description of each ^^^^_^ ^ெ component is extracted from the corresponding element of the “facial_blendshape_semantics.FACS_targets” array retrieved in block 520. Each ^^^^_^ ^ெ component is defined as a linear combination of elementary blendshapes ^^^^_^ ^{^} ,^{^} ^ associated with FACS Action Units, as shown in Eq.1: ^^^^_{ெ ^ ൌ ∑ ^ ^^}^^ ^_,^ ^^^^_^ ^{^} ,^{^} ^ (1) The ^^^_{^^ ^,^ ^ and ^^^^^^^ ^,^ ^ components are specified by the attributes of the k-th element of the} array. [0155] In a third sub-step, based on Eq.1, the morph targets ^^^^^ ^{^^௧^^^} ^ ^ associated with the avatar face mesh and having the topology of the reference mesh ^^^{^^^} are expressed as a weighted linear combination of the elementary morph targets ^^^^^ ^{^^,^^௧^^^} ^ ^ having the topology of the reference mesh ^^^{^^^} obtained in block 510, as shown in Eq.2: ^^^^ _{^^௧^^^ ^ ൌ ∑ ^ ^^}^^ ^_,^ ^^^^ ^{^^,^^௧^^^} ^_,^ (2) [0156] In a fourth sub-step, the the same topology as ^^^{^^^} , is synthesized as the linear combination of the blendshapes ^^^^_{^ weighted by the corresponding weights ^^^^^ retrieved in block 520, yielding the desired mesh} ^^^{^^௧^^^,^௫^^}, as shown in Eq.3: ^_{^^^௧^^^,^௫^^ ൌ ∑ ^^ ^^^^} ^^௧^^^ ^ _{^ ^} (3) [0157] This mesh has the in the “MPEG_node_avatar” extension and the reference topology defined by the reference mesh of the application. This mesh may be rendered by the application with the desired facial expression of the avatar. Recognizing a Facial Expression on the Avatar Mesh [0158] FIG.6 is a flowchart illustrating an example process for recognition of an emotion expressed by an avatar according to some embodiments. FIG.6 shows an example for parsing and processing of scene description elements for the recognition of an emotion expressed by an avatar based on a description of the facial expression semantics. [0159] In block 610, the application parses the scene description to extract the elements relevant to the computation of the FACS blendshape weights used to represent the expression of the avatar face mesh M. A first such element is the set of facial blendshapes ^^^^^_^ ^ெ^ associated to this mesh, encoded in the “targets” attribute of the mesh primitive that describes the face region of the avatar mesh. A second such element is the set of weights ^^^_^^ corresponding to the mesh blendshapes ^^^^^_^ ^ெ^. A third such element is the description of the semantics of a subset of the above blendshapes involved in the synthesis of the facial expression of the avatar face mesh. This description is encoded in the “facial_blendshape_semantics” attribute of the “MPEG_node_avatar” extension. This description is provided as a mapping of each ^^^^^_^ ^ெ^ to a linearly weighted combination of FACS Action Unit blendshapes ^^^^^_^ ^{^} ,^{^} ^ ^ with corresponding weights ^^^_^ ^{^} ,^{^} ^ ^, corresponding to the activations of facial muscles. In block 620, based on the elements retrieved in block 610, the application computes the weights associated with the FACS blendshapes in the facial expression of the avatar face mesh. Based on the information retrieved in block 610, the k-th blendshape ^^^^_^ ^ெ of the avatar face mesh may be expressed as a linear combination of FACS Action Unit blendshapes as shown in Eq.4: ^^^^_{ெ ^ ൌ ∑ ^ ^^}^^ ^_,^ ^^^^_^ ^{^} ,_^ ^{^} (4) [0161] The deformation ^^^^^ெ of the avatar mesh M resulting from the facial expression specified in the avatar node of the scene description is formed by linearly combining the morph targets (^^^^_^ ^ெ) of the avatar face mesh weighted by their corresponding weights ^^^_^^. Expressing each ^^^^_^ ^ெ as a function of its FACS Action Unit components using Eq.4 yields Eq.5: ^_{^^^ெ ൌ ∑ ^ ^^^ ∑} ^^ ^^ ^ _^^^,^ ^^^^_^,^ (5) [0162] This expression may be (^^^^_^ ^{^} ,_^ ^{^}), as shown in Eq.6: ^_{^^^ெ ൌ ∑^ ^∑ ^ ^^^ ^^}^^ ^_,^ ൧ ^^^^_^ ^{^} ,_^ ^{^} (6) [0163] Eq.6 decomposes the Action Unit blendshapes (^^^^_{^^ ^,^ ) with corresponding weights ∑ ^ ^^^ ^^^,^} . [0164] In block 630, the emotion expressed by the avatar is classified as a function of the FACS Action Unit decomposition computed in block 620. For instance, an application may hold a specification of each emotion that the application may recognize as a linear combination of FACS Action Unit weights, and combinations that fall within a range of weight values may be classified as particular emotions. For some embodiments, the classification may be performed on the basis of a pre-determined specification of each emotion as a set of AU weight ranges. For example, surprise may be specified in the application as a combination of: ^ Inner Brow Raiser Action Unit with a weight in the range [0.7, 1.0] ^ Outer Brow Raiser Action Unit with a weight in the range [0.5, 0.9] ^ Upper Lid Raiser Action Unit with a weight in the range [0.2, 0.4] ^ Jaw Drop Action Unit with a weight in the range [0.5, 1.0] [0165] The application may classify the considered expression of the avatar face mesh as surprise if the weights of the FACS Action Units in the decomposition of BS^M obtained in block 620 match the above range values. By applying similar classification schemes for other emotions or semantic categories of facial expressions, an application is able to label facial expressions of an avatar. [0166] FIG. 7 is a flowchart showing an example of synthesizing a facial expression on an avatar according to some embodiments. For some embodiments, an example process 700 may include obtaining 702 information corresponding to an avatar, wherein the information includes an avatar face mesh, an avatar face mesh, one or more morph targets and associated weights, and one or more facial semantics. For some embodiments, the example process 700 may further include re-topologizing 704 the avatar face mesh to a topology of the reference face mesh. For some embodiments, the example process 700 may further include performing 706 a deformation transfer process to transfer the morph targets with the facial semantics from the reference face mesh to the avatar face mesh. For some embodiments, the example process 700 may further include linearly combining 708 the transferred morph targets on the avatar face mesh to synthesize a facial expression. [0167] FIG.8 is a flowchart showing an example of categorizing a facial expression on an avatar according to some embodiments. For some embodiments, an example process 800 may include obtaining 802 information corresponding to an avatar, wherein the information includes an avatar face mesh, one or more morph targets and associated weights, and one or more facial semantics, and wherein the one or more facial semantics describe a deformation of the avatar face mesh. For some embodiments, the example process 800 may further include determining 804 a set of generic morph targets and associated weights corresponding to the deformation of the avatar face mesh. For some embodiments, the example process 800 may further include categorizing 806 the set of generic morph target weights as a facial expression. [0168] FIG. 9 is a flowchart showing an example of parsing information corresponding to a facial expression on an avatar according to some embodiments. For some embodiments, an example process 900 may include obtaining 902 information corresponding to an avatar. For some embodiments, the example process 900 may further include determining 904 that the information includes node information corresponding to an avatar node. For some embodiments, the example process 900 may further include determining 906 that the node information includes facial semantics information corresponding to morph target attributes of the avatar. For some embodiments, the example process 900 may further include parsing 908 the information corresponding to a subset of the morph target attributes, wherein the subset represents facial deformations. For some embodiments, the example process 900 may further include parsing 910 the information corresponding to weights and names of generic morph targets describing semantics of the morph target attributes. [0169] FIG.10 is a flowchart showing an example of generating information corresponding to a facial expression on an avatar according to some embodiments. For some embodiments, an example process 1000 may include selecting 1002 a facial expression for use with an avatar. For some embodiments, the example process 1000 may further include determining 1004 one or more morph targets and associated weights corresponding to the facial expression. For some embodiments, the example process 1000 may further include generating 1006 information corresponding to the avatar, wherein the information includes an avatar face mesh, the one or more morph targets and the associated weights, and one or more facial semantics. For some embodiments, the example process 1000 may further include communicating 1008 to a device the information corresponding to the avatar. [0170] 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) / 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. [0171] A first example method in accordance with some embodiments may include: obtaining information corresponding to an avatar, wherein the information includes an avatar face mesh, one or more morph targets and associated weights, and one or more facial semantics, and wherein the one or more facial semantics describe a deformation of the avatar face mesh; determining a set of generic morph targets and associated weights corresponding to the deformation of the avatar face mesh; and categorizing the set of generic morph target weights as a facial expression. [0172] In some embodiments of the first example method, determining the set of morph target weights corresponding to the deformation of the avatar face mesh includes: expressing the facial expression of the avatar face mesh using a linear combination of a subset of the one or more morph targets and associated weights; expressing each of the one or more morph targets as a weighted linear combination of generic morph targets; and expressing the avatar face mesh using a weighted linear combination of the generic morph targets. [0173] In some embodiments of the first example method, categorizing the set of morph target weights includes determining that at least one of the set of generic morph target weights is within a range associated with a category of the facial expression. [0174] In some embodiments of the first example method, the facial expression is described by the obtained information corresponding to the avatar. [0175] In some embodiments of the first example method, at least one of the one or more morph targets is a blendshape. [0176] In some embodiments of the first example method, the facial semantic is a Facial Action Coding System (FACS) blendshape semantic. [0177] 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. [0178] A second example method in accordance with some embodiments may include: obtaining information corresponding to an avatar, wherein the information includes an avatar face mesh, one or more morph targets and associated weights, and one or more facial semantics; re-topologizing the avatar face mesh to a topology of a reference face mesh; performing a deformation transfer process to transfer the morph targets with the facial semantics from the reference face mesh to the avatar face mesh; and linearly combining the transferred morph targets on the avatar face mesh to synthesize a facial expression. [0179] In some embodiments of the second example method, each of the facial semantics include a description of at least one of the one or more morph targets. [0180] In some embodiments of the second example method, each of the one or more morph targets represent a deformation of a face of the avatar, each of the facial semantics describe and correspond to one of the one or more morph targets, and each of the facial semantics include a decomposition and linear combination of two or more generic morph targets. [0181] In some embodiments of the second example method, the linear combination includes a linear combination of two or more FACS Action Unit blendshapes. [0182] In some embodiments of the second example method, re-topologizing the avatar face mesh to the topology of the reference face mesh includes: mapping each vertex of the reference face mesh to a location in the avatar face mesh; and replacing a location of each vertex of the reference face mesh with the mapped location in the avatar face mesh to warp the reference face mesh to a geometry of the avatar face mesh. [0183] In some embodiments of the second example method, performing the deformation transfer process includes: determining a set of geometric transforms, wherein each transform of the set of geometric transforms warps a triangle of the reference face mesh at rest to the triangle of the reference face mesh in which a corresponding morph target has been added; and applying the set of geometric transforms to the re- topologized avatar face mesh. [0184] In some embodiments of the second example method, linearly combining the transferred morph targets on the avatar face mesh includes: extracting a subset of the one or more morph targets corresponding to the facial expression; extracting a semantic description corresponding to at least one of the one or more morph targets; expressing each morph target of the subset of the one or more morph targets as a weighted linear combination of one or more generic morph targets; and performing a weighted linear combination of the weighted linear combinations of one or more generic morph targets of the subset. [0185] In some embodiments of the second example method, the facial expression is described by the obtained information corresponding to the avatar. [0186] In some embodiments of the second example method, at least one of the one or more morph targets is a blendshape. [0187] In some embodiments of the second example method, the facial semantic is a Facial Action Coding System (FACS) blendshape semantic. [0188] 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 the method of any one of the methods listed above. [0189] A third example method in accordance with some embodiments may include: obtaining information corresponding to an avatar, determining that the information includes node information corresponding to MPEG_node_avatar extension; determining that the node information includes semantics information corresponding to a facial_blendshape_semantics attribute; parsing the information corresponding to the avatar for target_indexes and FACS_targets attributes; and parsing the information corresponding to the avatar for AU_names and AU_weights FACS Action Unit descriptors in a FACS_targets array; [0190] A third 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. [0191] A fourth example method in accordance with some embodiments may include: obtaining information corresponding to an avatar, determining that the information includes node information corresponding to an avatar node; determining that the node information includes semantics information corresponding to morph target attributes of the avatar; parsing the information corresponding to a subset of the morph target attributes, wherein the subset represents facial deformations; and parsing the information corresponding to weights and names of generic morph targets describing semantics of the morph target attributes. [0192] A fourth 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. [0193] A fifth example method in accordance with some embodiments may include: selecting a facial expression for use with an avatar; determining one or more morph targets and associated weights corresponding to the facial expression; generating information corresponding to the avatar, wherein the information includes an avatar face mesh, the one or more morph targets and the associated weights, and one or more facial semantics; communicating to a device the information corresponding to the avatar. [0194] In some embodiments of the fifth example method, at least one of the one or more morph targets is a blendshape. [0195] In some embodiments of the fifth example method, the facial semantic is a Facial Action Coding System (FACS) blendshape semantic. [0196] A fifth 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. [0197] A sixth example apparatus in accordance with some embodiments may include at least one processor configured to perform the method of any one of the methods listed above. [0198] A seventh 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. [0199] An eighth 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. [0200] An example single in accordance with some embodiments may include information corresponding to an avatar, generated according to any one of the methods listed above. [0201] This disclosure 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 disclosure 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. [0202] The aspects described and contemplated in this disclosure 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. [0203] 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. [0204] Various numeric values may be used in the present disclosure, for example. The specific values are for example purposes and the aspects described are not limited to these specific values. [0205] 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. [0206] 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. [0207] 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. [0208] 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 disclosure are not necessarily all referring to the same embodiment. [0209] Additionally, this disclosure 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. [0210] Further, this disclosure 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. [0211] Additionally, this disclosure 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. [0212] 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. [0213] 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. [0214] 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. [0215] 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. [0216] 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

CLAIMS 1. A method comprising: obtaining information corresponding to an avatar, wherein the information comprises an avatar face mesh, one or more morph targets and associated weights, and one or more facial semantics, and wherein the one or more facial semantics describe a deformation of the avatar face mesh; determining a set of generic morph targets and associated weights corresponding to the deformation of the avatar face mesh; and categorizing the set of generic morph target weights as a facial expression.

2. The method of claim 1, wherein determining the set of morph target weights corresponding to the deformation of the avatar face mesh comprises: expressing the facial expression of the avatar face mesh using a linear combination of a subset of the one or more morph targets and associated weights; expressing each of the one or more morph targets as a weighted linear combination of generic morph targets; and expressing the avatar face mesh using a weighted linear combination of the generic morph targets.

3. The method of any one of claims 1-2, wherein categorizing the set of morph target weights comprises determining that at least one of the set of generic morph target weights is within a range associated with a category of the facial expression.

4. The method of any one of claims 1-3, wherein the facial expression is described by the obtained information corresponding to the avatar.

5. The method of any one of claims 1-4, wherein at least one of the one or more morph targets is a blendshape.

6. The method of any one of claims 1-5, wherein the facial semantic is a Facial Action Coding System (FACS) blendshape semantic.

7. 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 6.

8. A method comprising: obtaining information corresponding to an avatar, wherein the information comprises an avatar face mesh, one or more morph targets and associated weights, and one or more facial semantics; re-topologizing the avatar face mesh to a topology of a reference face mesh; performing a deformation transfer process to transfer the morph targets with the facial semantics from the reference face mesh to the avatar face mesh; and linearly combining the transferred morph targets on the avatar face mesh to synthesize a facial expression.

9. The method of claim 8, wherein each of the facial semantics comprise a description of at least one of the one or more morph targets.

10. The method of any one of claims 8-9, wherein each of the one or more morph targets represent a deformation of a face of the avatar, wherein each of the facial semantics describe and correspond to one of the one or more morph targets, and wherein each of the facial semantics comprise a decomposition and linear combination of two or more generic morph targets.

11. The method of claim 10, wherein the linear combination comprises a linear combination of two or more FACS Action Unit blendshapes.

12. The method of any one of claims 8-11, wherein re-topologizing the avatar face mesh to the topology of the reference face mesh comprises: mapping each vertex of the reference face mesh to a location in the avatar face mesh; and replacing a location of each vertex of the reference face mesh with the mapped location in the avatar face mesh to warp the reference face mesh to a geometry of the avatar face mesh.

13. The method of any one of claims 8-12, wherein performing the deformation transfer process comprises: determining a set of geometric transforms, wherein each transform of the set of geometric transforms warps a triangle of the reference face mesh at rest to the triangle of the reference face mesh in which a corresponding morph target has been added; and applying the set of geometric transforms to the re-topologized avatar face mesh.

14. The method of any one of claims 8-13, wherein linearly combining the transferred morph targets on the avatar face mesh comprises: extracting a subset of the one or more morph targets corresponding to the facial expression; extracting a semantic description corresponding to at least one of the one or more morph targets; expressing each morph target of the subset of the one or more morph targets as a weighted linear combination of one or more generic morph targets; and performing a weighted linear combination of the weighted linear combinations of one or more generic morph targets of the subset.

15. The method of any one of claims 8-14, wherein the facial expression is described by the obtained information corresponding to the avatar.

16. The method of any one of claims 8-15, wherein at least one of the one or more morph targets is a blendshape.

17. The method of any one of claims 8-16, wherein the facial semantic is a Facial Action Coding System (FACS) blendshape semantic.

18. 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 8 through 17.

19. A method comprising: obtaining information corresponding to an avatar, determining that the information comprises node information corresponding to MPEG_node_avatar extension; determining that the node information comprises semantics information corresponding to a facial_blendshape_semantics attribute; parsing the information corresponding to the avatar for target_indexes and FACS_targets attributes; and parsing the information corresponding to the avatar for AU_names and AU_weights FACS Action Unit descriptors in a FACS_targets array.

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 claim 19.

21. A method comprising: obtaining information corresponding to an avatar, determining that the information comprises node information corresponding to an avatar node; determining that the node information comprises semantics information corresponding to morph target attributes of the avatar; parsing the information corresponding to a subset of the morph target attributes, wherein the subset represents facial deformations; and parsing the information corresponding to weights and names of generic morph targets describing semantics of the morph target attributes.

22. 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 claim 21.

23. A method comprising: selecting a facial expression for use with an avatar; determining one or more morph targets and associated weights corresponding to the facial expression; generating information corresponding to the avatar, wherein the information comprises an avatar face mesh, the one or more morph targets and the associated weights, and one or more facial semantics; communicating to a device the information corresponding to the avatar.

24. The method of claim 23, wherein at least one of the one or more morph targets is a blendshape.

25. The method of any one of claims 23-24, wherein the facial semantic is a Facial Action Coding System (FACS) blendshape semantic.

26. 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 23 through 25.

27. A method comprising: obtaining information corresponding to an avatar, wherein the information comprises an avatar face mesh in a neutral pose, a description of semantics of each avatar blendshape as a linear combination of reference blendshapes of a reference blendshape model, and a weight of each avatar blendshape; re-topologizing the avatar face mesh in the neutral pose to a topology of a template face mesh with a predetermined topology; performing a deformation transfer process to transfer the reference blendshapes of the template face mesh with the predetermined topology to the retopologized avatar face mesh; and reconstructing the blendshapes of the avatar face mesh by linearly combining the transferred reference blendshapes on the retopologized avatar face mesh according to their semantic description.

28. The method of claims 27, wherein each of the reference blendshapes represents a deformation of a face of the avatar.

29. The method of claim 27, wherein the linear combination comprises a linear combination of two or more FACS Action Unit blendshapes.

30. The method of any one of claims 27-29, wherein re-topologizing the avatar face mesh in the neutral pose to the topology of the template face mesh comprises: mapping each vertex of the template face mesh to a location in the avatar face mesh; and replacing a location of each vertex of the template face mesh with the mapped location in the avatar face mesh to warp the template face mesh to a geometry of the avatar face mesh.

31. 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 27 through 30.

32. An apparatus comprising at least one processor configured to perform the method of any one of claims 1-6, 8-17, 19, 21, 23-25, and 27-30.

33. An apparatus comprising a computer-readable medium storing instructions for causing one or more processors to perform the method of any one of claims 1-6, 8-17, 19, 21, 23-25, and 27-30.

34. 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 1-6, 8-17, 19, 21, 23-25, and 27-30.

35. A signal including information corresponding to an avatar, generated according to any one of claims 1-6, 8-17, 19, 21, 23-25, and 27-30.