WO2025212413A1

WO2025212413A1 - Extension mechanisms for jpeg ai sub-streams

Info

Publication number: WO2025212413A1
Application number: PCT/US2025/021989
Authority: WO
Inventors: Ye-Kui Wang
Original assignee: ByteDance Inc
Current assignee: ByteDance Inc
Priority date: 2024-04-04
Filing date: 2025-03-28
Publication date: 2025-10-09
Anticipated expiration: 2026-10-04
Also published as: WO2025212408A1

Abstract

A mechanism for processing video data is disclosed. The mechanism includes determining that a Joint Photographic Experts Group (JPEG) Artificial Intelligence (AI) sub-stream includes a sub-stream marker identifier (ID) syntax element, a sub-stream size syntax element, and sub-stream payload data. A conversion is performed between a visual media data and the JPEG AI sub-stream based on the determination.

Description

Extension Mechanisms For JPEG Al Sub-streams

CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This patent application claims the benefit of U.S. Patent Application No. 63/631,717 filed on April 9, 2024, U.S. Patent Application No. 63/631,093 filed on April 8, 2024, and U.S. Patent Application No. 63/574,719 filed on April 4, 2024, which are hereby incorporated by reference in their entireties.

TECHNICAL FIELD

[0002] The present disclosure relates to generation, storage, and consumption of digital audio video media information in a file format.

BACKGROUND

[0003] Digital video accounts for the largest bandwidth used on the Internet and other digital communication networks. As the number of connected user devices capable of receiving and displaying video increases, the bandwidth demand for digital video usage is likely to continue to grow.

SUMMARY

[0004] A first aspect relates to a method for processing media data comprising: determining that a Joint Photographic Experts Group (JPEG) Artificial Intelligence (Al) sub-strcam includes a sub-strcam marker identifier (ID) syntax element, a sub-stream size syntax element, and sub-stream payload data; and performing a conversion between a visual media data and the JPEG Al sub-stream based on the determination.

[0005] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the sub-stream marker ID syntax element comprises X bits.

[0006] Optionally, in any of the preceding aspects, another implementation of the aspect provides that X is equal to 16.

[0007] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the sub-stream size syntax element indicates a size of the sub-stream payload in bytes.

[0008] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the sub-bitstream size syntax element indicates a size of the sub-bitstream payload in bits.

[0009] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the sub-stream payload data comprises the JPEG Al sub-stream excluding the sub-stream marker ID syntax element.

[0010] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the sub-stream payload data comprises the JPEG Al sub-stream excluding the sub-stream marker ID syntax element and the sub-stream size syntax element.

[0011] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the sub-stream payload data comprises the JPEG Al sub-stream excluding the sub-stream marker ID syntax element, the sub-stream size syntax element, and byte alignment bits immediately following the sub-stream size syntax element.

[0012] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the sub-stream size syntax element is coded as an unsigned integer using N bits (u(N)), where N is 8, 16, 24, or 32.

[0013] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the sub-stream size syntax element is coded as an unsigned exponential-Golomb-coded value of a variable number of bits (ue(v)).

[0014] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the sub-stream size syntax element specifies a size of the JPEG Al sub-stream excluding the sub-stream marker ID syntax element, in bytes, minus 1.

[0015] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the JPEG Al sub-stream optionally includes byte alignment bits, and wherein the byte alignment bits ensure that a total number of bits in the JPEG Al sub-stream before the sub-stream pay load data is an integer multiple of 8.

[0016] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the sub-stream payload data excludes the sub-stream size syntax element.

[0017] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the JPEG Al sub-stream optionally includes data extension bits, wherein the data extension bits permit versions of the JPEG Al standard after version 1 to add additional data with specific syntax and semantics to the JPEG Al substream.

[0018] Optionally , in any of the preceding aspects, another implementation of the aspect provides that a number of the data extension bits is included in the JPEG Al sub-stream, and wherein the number of data extension bits are configured to control a presence and the number of data extension bits.

[0019] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the number of bits is included in the JPEG Al sub-stream immediately before the data extension bits.

[0020] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the by te alignment bits ensure that the total number of bits in the JPEG Al sub-stream is an integer multiple of 8.

[0021] Optionally , in any of the preceding aspects, another implementation of the aspect provides that a presence of the data extension bits and the byte alignment bits in the JPEG Al sub-stream is collectively controlled by a single condition, and wherein the data extension bits and the byte alignment bits are collectively represented in the JPEG Al sub-stream by a single syntax element or instances of a single syntax element.

[0022] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the condition is whether a number of bits in the JPEG Al sub-stream is less than indicated by the sub-stream size syntax element.

[0023] Optionally , in any of the preceding aspects, another implementation of the aspect provides that the JPEG Al sub-stream comprises one of a picture header sub-stream, a tools header sub-stream, a rendering information sub-stream, a quality map sub-stream, a hyper tensor sub-stream, a primary residual sub-stream, a secondary residual sub-stream, or one of a plurality of reserved types of sub-streams.

[0024] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the sub-stream size syntax element is designated ss size minusl, and wherein a syntax element designated additional_ss_bit[ i ] collectively represents the byte alignment bits and the data extension bits optionally included in the JPEG Al sub-stream.

[0025] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the additional_ss_bit[ i ] is only present in the JPEG Al sub-stream when the ss size minusl plus 1, multiplied by 8, is greater than a total number of bits for all syntax elements starting from the ss size minusl up to and excluding the additional_ss_bit[ 0 ]. when present, in the JPEG Al sub-stream.

[0026] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the total number of bits for all syntax elements is a variable designated NumPhBitsAtThisPoint.

[0027] Optionally, in any of the preceding aspects, another implementation of the aspect provides that a number of present instances of the additional_ss_bit[ i ] is equal to the ss size minusl plus 1, multiplied by 8, minus the NumPhBitsAtThisPoint.

[0028] Optionally, in any of the preceding aspects, another implementation of the aspect provides that a value of the NumPhBitsAtThisPoint is less than or equal to the ss size minusl plus 1, multiplied by 8.

[0029] Optionally, in any of the preceding aspects, another implementation of the aspect provides that a value of the ss size minusl plus 1, multiplied by 8, minus the NumPhBitsAtThisPoint is less than 8 in codestreams conforming to version 1 of the JPEG Al standard.

[0030] Optionally, in any of the preceding aspects, another implementation of the aspect provides that a value of the ss size minusl plus 1, multiplied by 8, minus the NumPhBitsAtThisPoint is permitted by a decoder to be greater than or equal to 8, and wherein values of all present instances of the additional_ss_bit[ i ] are ignored by the decoder.

[0031] Optionally, in any of the preceding aspects, another implementation of the aspect provides that instances of the additional_ss_bit[ i ] are extension bits only, byte alignment bits only, or extension bits followed by byte alignment bits.

[0032] Optionally, in any' of the preceding aspects, another implementation of the aspect provides that the conversion includes encoding the visual media data into the bitstream.

[0033] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the conversion includes decoding the visual media data from the bitstream.

[0034] A second aspect relates to an apparatus for processing video data comprising: a processor; and a non- transitory memory with instructions thereon, wherein the instructions upon execution by the processor, cause the processor to perform the method of any of disclosed aspects. [0035] A third aspect relates to a non-transitory computer readable medium comprising a computer program product for use by a video coding device, the computer program product comprising computer executable instructions stored on the non-transitory computer readable medium such that when executed by a processor cause the video coding device to perform the method of any of the disclosed aspects.

[0036] A fourth aspect relates to a non-transitory computer-readable recording medium storing a bitstream of a video which is generated by a method performed by a video processing apparatus, wherein the method comprises: determining that a Joint Photographic Experts Group (JPEG) Artificial Intelligence (Al) sub-stream includes a sub-stream marker identifier (ID) syntax element, a sub-stream size syntax element, and sub-stream payload data; and generating the JPEG Al sub-stream based on the determination.

[0037] A fifth aspect relates to a method for storing bitstream of a video comprising: determining that a Joint Photographic Experts Group (JPEG) Artificial Intelligence (Al) sub-stream includes a sub-stream marker identifier (ID) syntax element, a sub-stream size syntax element, and sub-stream payload data; generating the JPEG Al substream based on the determination; and storing the bitstream in a non-transitory computer-readable recording medium.

[0038] A sixth aspect relates to a method, apparatus, or system described in the present disclosure.

[0039] For the purpose of clarity, any one of the foregoing embodiments may be combined with any one or more of the other foregoing embodiments to create a new embodiment within the scope of the present disclosure.

[0040] These and other features will be more clearly understood from the following detailed description taken in conjunction with the accompany ing drawings and claims.

BRIEF DESCRIPTION OF THE DRAWINGS

[0041] For a more complete understanding of this disclosure, reference is now made to the following brief description, taken in connection with the accompanying drawings and detailed description, wherein like reference numerals represent like parts.

[0042] FIG. 1 is a block diagram showing an example video processing system.

[0043] FIG. 2 is a block diagram of an example video processing apparatus.

[0044] FIG. 3 is a flowchart for an example method of video processing.

[0045] FIG. 4 is a block diagram that illustrates an example video coding system.

[0046] FIG. 5 is a block diagram that illustrates an example encoder.

[0047] FIG. 6 is a block diagram that illustrates an example decoder.

[0048] FIG. 7 is a schematic diagram of an example encoder.

DETAILED DESCRIPTION

[0049] It should be understood at the outset that although an illustrative implementation of one or more embodiments are provided below, the disclosed systems and/or methods may be implemented using any number of techniques, whether currently known or yet to be developed. The disclosure should in no way be limited to the illustrative implementations, drawings, and techniques illustrated below, including the exemplary designs and implementations illustrated and described herein, but may be modified within the scope of the appended claims along with their full scope of equivalents.

1. Initial discussion

[0050] This disclosure is related to neural network (NN)-based image and video coding. Specifically, this disclosure is related to extensibility for sub-streams in neural network (NN)-based image or video bitstreams, such as a Joint Photographic Experts Group (JPEG) Artificial Intelligence (Al) codestream, which may also be referred to as a bitstream or a codestream. The ideas may be applied individually or in various combinations, for image and/or video coding methods and specifications.

2. Further discussion

[0051] Deep learning has developed rapidly in a variety of areas, especially in computer vision and image processing. Inspired from the great success of deep learning technology to computer vision areas, many researchers have shifted their attention from image/video compression techniques to neural image/video compression technologies. Neural network is designed with the interdisciplinary research of neuroscience and mathematics. It has shown strong capabilities in the context of non-linear transform and classification. Neural network-based image/video compression technology has gained significant progress. It is reported that an example neural networkbased image compression algorithm achieves comparable rate-distortion (R-D) performance with Versatile Video Coding (WC), a video coding standard developed by Joint Video Experts Team (JVET) with experts from motion picture experts group (MPEG) and Video Coding Experts Group (VCEG). With the performance of neural image compression continually being improved, neural network-based video compression has become an actively developing research area. However, neural network-based video coding still remains in its infancy due to the inherent difficulty of the problem.

2.1 Image/video compression

[0052] Image/video compression (also referred to as image/video coding) usually refers to the computing technology that compresses image or video into binary code to facilitate storage and transmission. The binary codes may or may not support losslessly reconstructing the original image or video, termed lossless compression and lossy compression. Most of the efforts are devoted to lossy compression since lossless reconstruction is not necessary in most scenarios. Usually the performance of image or video compression algorithms is evaluated from two aspects, including compression ratio and reconstruction quality. Compression ratio is directly related to the number of binary codes, the less the better; while reconstruction quality is measured by comparing the reconstructed image or video with the original image or video, the higher the better.

[0053] Image/video compression techniques can be divided into two branches, including the classical video coding methods and the neural -network -based video compression methods. Classical video coding schemes adopt transform-based solutions, in which researchers have exploited statistical dependency in the latent variables (e.g., discrete cosine transform (DCT) or wavelet coefficients) by carefully hand-engineering entropy codes modeling the dependencies in the quantized regime. Neural network-based video compression is in two flavors, neural network-based coding tools and end-to-end neural network-based video compression. The former is embedded into classical video codecs as coding tools and only serves as part of the framework, while the latter is a separate framework developed based on neural networks without depending on classical video codecs.

[0054] A series of classical video coding standards have been developed to accommodate the increasing visual content. The international standardization organizations International Organization for Standardization (ISO) / International Electrotechnical Commission (IEC) has tw o expert groups namely Joint Photographic Experts Group (JPEG) and Moving Picture Experts Group (MPEG), and International Telecommunication Union (ITU) telecommunication standardization sector (ITU-T) also has its own Video Coding Experts Group (VCEG) which is for standardization of image or video coding technology. The influential video coding standards published by these organizations include JPEG, JPEG 2000, H.262. H.264/Advanced Video Coding (AVC) and H.265/High Efficiency Video Coding (HEVC). After H.265/HEVC, the Joint Video Experts Team (JVET) formed by MPEG and VCEG began working on a video coding standard Versatile Video Coding (WC). The first version of WC was released in July 2020. An average of 50% bitrate reduction is reported by WC under the same visual quality compared with HEVC.

[0055] A number of researchers are w orkmg on neural network-based image coding used in neural netw ork- based image/video compression. But the netw ork architectures used in example designs are relatively shallow, and the performance is not satisfactory'. Benefit from the abundance of data and the support of powerful computing resources, neural network-based methods are better exploited in a variety of applications. At present, neural network-based image/video compression has shown promising improvements, and confirmed its feasibility. Nevertheless, this technology is still far from mature and a lot of challenges should be addressed.

2.2. Neural networks

[0056] Neural networks, also known as artificial neural networks (ANN), are the computational models used in machine learning technology which are usually composed of multiple processing layers and each layer is composed of multiple simple but non-linear basic computational units. One benefit of such deep networks is believed to be the capacity for processing data with multiple levels of abstraction and converting data into different kinds of representations. Note that these representations are not manually designed; instead, the deep network including the processing layers is learned from massive data using a general machine learning procedure. Deep learning eliminates the necessity of handcrafted representations, and thus is regarded useful especially' for processing natively unstructured data, such as acoustic and visual signal, yvhilst processing such data has been a longstanding difficulty in the artificial intelligence field.

2.3. Neural networks for image and video compression

[0057] Example neural networks for image compression methods can be classified in two categories, including pixel probability modeling and auto-encoder. The former one belongs to the predictive coding strategy, while the latter one is the transform-based solution. Sometimes, these two methods are combined together. [0058] Similar to classical video coding technologies, neural image compression serves as the foundation of intra compression in neural network-based video compression, thus development of neural network-based video compression technology comes later than neural network-based image compression, but needs far more efforts to solve the challenges due to its complexity . A few researchers are working on neural network-based video compression schemes. Compared with image compression, video compression needs efficient methods to remove inter-picture redundancy. Inter-picture prediction is then a key step in these works. Motion estimation and compensation is used, but is not implemented by trained neural networks until recently.

[0059] Studies on neural network-based video compression can be divided into two categories according to the targeted scenarios including random access and the low-latency. In random access case, the decoding can be started from any point of the sequence, the entire sequence is divided into multiple individual segments, and each segment can be decoded independently. The low-latency case aims to reduce decoding time, and thereby temporally previous frames can be used as reference frames to decode subsequent frames.

2.4. The JPEG Al image coding standard and signalling of JPEG Al sub-streams

[0060] The JPEG Al image coding standard is an image coding standard governed by the JPEG Working Group (WG), which is WG 1 of ISO/IEC Joint Technical Committee (JTC) 1 Subcommittee (SC) 29. The ISO/IEC number for the JPEG Al standard is ISO/IEC 6048.

[0061] An example JPEG Al draft specification utilizes some NN-based image coding methods described as mentioned above. Some of the features in the example JPEG Al specification, including signalling of various substreams, are described or summarized below.

2.4.1 (2.2) Specification of syntax functions and descriptors

[0062] The functions presented here are used in the sy ntactical description. These functions are expressed in terms of the value of a bitstream pointer that indicates the position of the next bit to be read by the decoding process from the bitstream.

[0063] read_bits( n ) reads the next n bits from the bitstream and advances the bitstream pointer by n bit positions. When n is equal to 0, read_bits( n ) is specified to return a value equal to 0 and to not advance the bitstream pointer.

[0064] read_bits_from_back( n ) reads the n bits from the end of a sub-stream in bitstream and move back the sub-stream bitstream pointer by n bit positions. When n is equal to 0, read_bits_from_back( n ) is specified to return a value equal to 0 and to not move the sub-stream bitstream pointer.

[0065] The following descriptors specify the parsing process of each sy ntax element:

- b(8): by te having any pattern of bit string (8 bits). The parsing process for this descriptor is specified by the return value of the function read_bits( 8 ).

- f(n) : fixed-pattern bit string using n bits written (from left to right) with the left bit first. The parsing process for this descriptor is specified by the return value of the function read_bits( n ). - i(n): signed integer using n bits. When n is “v” in the syntax table, the number of bits varies in a manner dependent on the value of other syntax elements. The parsing process for this descriptor is specified by the return value of the function read_bits( n ) interpreted as a two's complement integer representation with most significant bit written first.

- se(v): signed integer O-th order Exp-Golomb-coded syntax element with the left bit first. The parsing process for this descriptor is specified in clause Annex C with the order k equal to 0.

- u(n): unsigned integer using n bits. When n is “v” in the syntax table, the number of bits varies in a manner dependent on the value of other syntax elements. The parsing process for this descriptor is specified by the return value of the function read_bits( n ) interpreted as a binary representation of an unsigned integer with most significant bit written first.

- ub(n): unsigned integer using n bits. When n is V in the syntax table, the number of bits varies in a manner dependent on the value of other syntax elements. The parsing process for this descriptor is specified by the return value of the function read_bits_from_back( n ) interpreted as a binary representation of an unsigned integer w ith most significant bit written first.

2.4.2. (6.2) Code stream layout

[0066] The code stream is composed of six parts with byte boundary', which are:

1. SOC - Start Of Codestream marker;

2. PIH (Picture Header marker) followed by picture header;

3. TOH (Tools Header marker) followed by tools information;

4. SOQ (start of Quality map marker) followed by code stream

5. SOZ (Start of Z-stream marker) followed codestream of hyper tensor z, including z_Y and z_uv

6. SORp (Start of Residual stream for primary component marker) followed by codestream of primary component residual, which includes r_y;

7. SORs (Start of Residual stream for secondary component marker) followed by codestream of secondary component residual, which includes _w;

8. EOC - End Of Codestream marker.

The overall syntax structure of an image is:

[0067] Each codestream starts with a 16-bit marker. All markers used in this specification are as follows:

2.4.3. (6.3) Picture header

[0068] This sub-stream contains information about image height H. width W, latent space tiles location and sizes, control flags for each tool, scaling factors for primary and secondary component, modelldx - learnable model index and displacement for rate control parameters (fi_Y for primary and p_uv for secondary component).

2.4.2.1 (6.3.1) Syntax table

2.4.23 (6.3.2) Picture header semantics

[0069] Following service information is signalled:

[0070] picture header size is the number of bytes in the picture header excluding the first two- byte marker;

[0071] img width plus 64 specifies width of an input picture (from 64 to 65599);

[0072] img height plus 64 specifies height of the input picture (from 64 to 65599);

2.4.4. (6.4) Tools header

[0073] This optional sub-stream contains information about tools. When the tools_header() marker segment is not present in the bitstream, the following tool enabling flags are set to be 0: rvs enable flag, Isbs enable flag, grfs enable flag. gain_3D_enable_flag. icci enable flag, LEF enabled flag, EFE linear filter enabled flag, and EFE nonlinear filter enabled flag.

2.4.4.1 (6.4.1) Tools header syntax table

2.4.4.2 (6.4.2) Tools information semantics

[0074] tools hcadcr sizc is the number of bytes in the tools header excluding the first tw o-byte marker;

[0075] rvs_enable_flag[comp] - is a flag used in the RVS for comp component. 0 indicates RVS disabled, 1 indicates RVS turn on.

[0076] rvs_num_idx[comp] is an identificator for operation point, 0 means 1 threshold for RVS, 1 means 3 thresholds for RVS.

[0077] lsbs_enable_flag[comp] - is a flag used in the LSBS mode for comp component. 0 indicates LSBS disabled, 1 indicates LSBS turn on.

2.4.5. (6.5) Residual and hyper tensor coding

2.4.5.1 (6.5.1.1) Syntax table of hyper tensor

2.4.5.2 (6.5.1.2) Semantics of hyper tensor

[0078] z stream size is the number of bytes in the hyper tensor codestream excluding the first two-byte marker;

[0079] num threads z is the number of parallelly decodable sub-stream in the hy-per tensor codestream; the maximum value of num threads z is 128.

[0080] thread_offsets_z[i] is the number of bytes between the start of the hyper tensor sub-stream i and the start of the hyper tensor codestream (excluding the first two-byte marker). 2.4.5.3 (6.5.2.1) Syntax table of quality map information tensor

2.4.5.4 (6.5.2.2) Semantics of quality map information tensor

[0081] q_stream_size is the number of bytes in the quality map codestream excluding the first two-byte marker;

[0082] num threads q is the number of parallelly decodable sub-stream in the quality map codestream; the maximum value of num threads q is 128.

[0083] thread_offsets_q[i] is the number of bytes between the start of the quality map sub-stream i and the start of the quality map codestream (excluding the first two-byte marker).

2.4.5.S (6.5.3.1.1) Syntax table of primary residual tensor

2.4.S.6 (6.5.3.1.2) Semantics of primary residual tensor

[0084] r_primary_stream_size is the number of bytes in the primary’ component residual tensor codestream excluding the first two-byte marker;

[0085] num_threads_r_primary is the number of parallelly decodable sub-stream in primary component residual tensor codestream; the maximum value of num_threads_r_primary is 128 and is dependent on profiles and levels;

[0086] thread_offsets_r_primary[i] is the number of bytes between the start of the primary component residual tensor sub-stream i and the start of the primary component residual tensor codestream (excluding the first two-by tc marker);

2.4.5.7 (6.5.3.2.1) Syntax table of secondary residual tensor 2.4.5.8 (6.53.2.2) Semantics of secondary residual tensor

[0087] r secondary stream size is the number of bytes in the secondary component residual tensor codestream excluding the first two-byte marker;

[0088] num threads r secondary is the number of parallelly decodable sub-stream in secondary component residual tensor codestream; the maximum value of num threads r secondary is 128 and is dependens on profiles and levels;

[0089] thread offsets r secondary [i] is the number of bytes between the start of the secondary component residual tensor sub-stream i and the start of the secondary component residual tensor codestream (excluding the first two-byte marker);

3. Technical problems solved by disclosed technical solutions

[0090] JPEG Al sub-streams include the picture header sub-stream (the picturc headcrf) syntax structure), the tools header sub-stream (the tools_header()syntax structure), the rendering information sub-stream, the quality map sub-stream (the q_stream() syntax structure), the hy-per tensor sub-stream (the z_stream() syntax structure), the primary residual sub-stream (the r_primary_stream() syntax structure), the secondary residual sub-stream (the r_secondary_stream() syntax structure), and some reserved types of sub-streams associated with reserved substream markers. The picture header sub-stream, the primary residual sub-stream, and the secondary residual substream are mandatory, and all other sub-streams are indicated as optional by the table of markers.

[0091] In an example design of JPEG Al sub-streams, there lacks an extension mechanism that enables adding extension data in a future version of the JPEG Al standard in a manner that the extension data can be ignored by legacy JPEG Al decoders conforming to the current version of the standard and continue processing of the rest of the data in the sub-stream.

4. A listing of solutions and embodiments

[0092] To solve the above-described problems, methods as summarized below are disclosed. The aspects should be considered as examples to explain the general concepts and should not be interpreted in a narrow way. Furthermore, these examples can be applied individually or combined in any manner.

1) In one example, a sub-stream in a coded image or video bitstream of a standard, e.g., JPEG Al, is designed to consists at least the following parts: a. An X-bit marker syntax element specifying a sub-stream marker. i. In one example, X is equal to 16. b. A sub-stream size syntax element indicating the size of the sub-stream payload in bytes or bits, where the sub-stream payload could be either the sub-stream excluding the sub-stream marker or the sub-stream excluding the sub-stream marker and the size or the sub-stream excluding the sub-stream marker, the size, and the byte alignment bits immediately following the size. i. In one example, the sub-stream size syntax element is u(N)-coded, where N could be 8. 16, 24, or 32. ii. In another example, the sub-stream size syntax element is ue(v)-coded. where ue(v) coding is the same as specified in H.266/WC, which the also the same as in H.264/AVC and H.265/HEVC.

1. In another example, the ue(v)-coded sub-stream size syntax element specifies the size of the sub-stream excluding the marker syntax element, in bytes, minus 1. c. Optionally present byte alignment bits, which ensures that the total number of bits in the substrcam before the sub-strcam payload is an integer multiple of 8. d. The sub-stream payload, excluding the sub-stream size syntax element if the sub-stream size syntax element is considered as part of the sub-stream payload. e. Optionally present data extension bits, which allows future versions of the standard to add more data with specific syntax and semantics to the sub-stream. i. In one example, the number of data extension bits is also signalled in the sub-stream, e.g., immediately before the data extension bits, to control the presence and the number of data extension bits. f. Optionally present byte alignment bits, which ensures that the total number of bits in the substream is an integer multiple of 8. ) In one example, in the sub-stream design per item 1 above, the presence of the optionally present data extension bits and the optionally present byte alignment bits are collectively controlled by one condition and collectively represented by one syntax element or instances of one syntax element. a. In one example, the condition is whether the number of bits in the sub-stream is less than that indicated by the sub-stream size syntax element. ) In one example, the sub-stream is one of the picture header sub-stream, the tools header sub-stream, the rendering information sub-stream, the quality map sub-stream, the hyper tensor sub-stream, tire primary residual sub-stream, the secondary residual sub-stream, or one of the reserved types of sub-streams.) In one example, when the sub-stream is the picture header sub-stream, the marker syntax element is the PIH syntax element, the sub-stream size syntax element is the picture header size, and the syntax element that collectively represents the optionally present data extension bits and the optionally present byte alignment bits is the additional picturc hcadcr bits syntax element. a. In one example, the additional_picture_header_bits syntax element is only present when picture header size * 8 is greater than NumPhBitsAtThisPoint, wherein

NumPhBitsAtThisPoint is the total number of bits for all the syntax elements starting from the picture header size syntax element up to and excluding the additional_picture_header_bits syntax element, when present, in the picturc headerf ) syntax structure. b. In one example, it is specified that, when additional_picture_header_bits is present, its length, in bits, is picture header size * 8 - NumPhBitsAtThisPoint. c. In one example, it is specified that the value of NumPhBitsAtThisPoint shall be less than or equal to picture header size * 8. d. In one example, it is specified that, in codestreams conforming to version 1 of the JPEG Al standard, the value of picture header size * 8 - NumPhBitsAtThisPoint shall be less than 8. e. In one example, it is specified that, decoders shall allow the value of picture header size * 8 - NumPhBitsAtThisPoint to be greater than or equal to 8 and shall ignore the value of additional_picture_header_bits, when present. f. In one example, it is specified that, additional_picturc_hcadcr_bits can contain bits that arc all extension bits, are all byte alignment bits, or are extension bits followed by byte alignment bits.) In one example, when the sub-stream is the picture header sub-stream, the marker sy ntax element is the PIH syntax element, the sub-stream size syntax element is the picture header size, and the syntax element whose instances that collectively represent the optionally present data extension bits and the optionally present byte alignment bits is the additional_picture_header_bit[ i ] syntax element. a. In one example, the additional_picture header bit[ i ] syntax element is only present when picture header size * 8 is greater than NumPhBitsAtThisPoint, wherein

NumPhBitsAtThisPoint is the total number of bits for all the syntax elements starting from the picture header size syntax element up to and excluding the additional_picture_header_bit[ 0 ] sy ntax element, when present, in the picture_header( ) syntax structure. i. In one example, the additional_picture_header_bit[ i ] syntax element is only present when picture header size * 8 is greater than NumPhBitsAtThisPoint, wherein NumPhBitsAtThisPoint is the total number of bits for all the syntax elements starting from the first syntax element after all the byte alignment bits, if any, that immediately’ follow the picture header size syntax element, up to and excluding the additional_picture_header_bit[ 0 ] syntax element, when present, in the picture_header( ) syntax structure. b. In one example, the number of present instances of the additional_picture_header_bit[ i ] syntax element is equal to picture header size * 8 - NumPhBitsAtThisPoint. c. In one example, it is specified that the value of NumPhBitsAtThisPoint shall be less than or equal to picture header size * 8. d. In one example, it is specified that, in codestreams conforming to version 1 of the JPEG Al standard, the value of picture header size * 8 - NumPhBitsAtThisPoint shall be less than 8. e. In one example, it is specified that, decoders shall allow the value of picture header size * 8 - NumPhBitsAtThisPoint to be greater than or equal to 8 and shall ignore the values of all present instances of additional_picture_header_bit[ i ]. f. In one example, it is specified that instances of additional_picture_header_bit[ i ] can be extension bits only, byte alignment bits only, or be extension bits followed by byte alignment bits.

6) In one example, the sub-stream size syntax element is the ss size minus 1 syntax element, and the syntax element whose instances that collectively represent the optionally present data extension bits and the optionally present byte alignment bits is the additional ss bitf i ] syntax element. a. In one example, the additional ss bitf i ] syntax element is only present when

( ss size minusl + 1 ) * 8 is greater than NumPhBitsAtThisPoint, wherein

NumPhBitsAtThisPoint is the total number of bits for all the syntax elements starting from the ss size minusl syntax element up to and excluding the additional ss bitf 0 ] syntax element, when present, in the sub-stream. b. In one example, the number of present instances of the additional ss bitf i ] syntax element is equal to ( ss size minusl + 1 ) * 8 - NumPhBitsAtThisPoint. c. In one example, it is specified that the value of NumPhBitsAtThisPoint shall be less than or equal to ( ss size minusl + 1 ) * 8. d. In one example, it is specified that, in codestreams conforming to particular version of the JPEG Al standard, the value of ( ss size minusl + 1 ) * 8 - NumPhBitsAtThisPoint shall be less than 8. e. In one example, it is specified that, decoders shall allow the value of ( ss size minusl + 1 ) * 8 - NumPhBitsAtThisPoint to be greater than or equal to 8 and shall ignore the values of all present instances of additional ss bitf i ]. f. In one example, it is specified that instances of additional ss bitf i ] can be all extension bits, be all byte alignment bits, or be extension bits followed by byte alignment bits.

5. Embodiments

[0093] Below are some example embodiments for the aspects summarized in section 4. Most relevant parts that have been added or modified are shown in bold font, and some of the deleted parts are shown in italicized bold fonts. There may be some other changes that are editorial in nature and thus not highlighted.

5.1 Embodiment 1

[0094] This embodiment is for some of the items summarized above in Section 4.

5.1.1. (6.3) Picture header

[0095] This sub-stream contains information about image height H, width W. latent space tiles location and sizes, control flags for each tool, scaling factors for primary and secondary component, model! dx - learnable model index and displacement for rate control parameters ( ?_y for primary and _uv for secondary component). 2.4.2.1 (6.3.1) Syntax table

2.4.2.3 (6.3.2) Picture header semantics

[0096] Following sendee information is signalled:

[0097] picture header size is the number of bytes in the picture header excluding the first two-byte marker;

[0098] Alternatively: picture header size is ue(v)-coded, where ue(v) coding is the same as specified in H.266/WC, which the also the same as in H.264/AVC and H.265/HEVC.

[0099] img width plus 64 specifies width of an input picture (from 64 to 65599);

[0100] img height plus 64 specifies height of the input picture (from 64 to 65599);

[0101] When present, additional picture header bits could have any value.

[0102] Let the variable NumPhBitsAtThisPoint be the total number of bits for all the syntax elements starting from the picture header size syntax element up to and excluding the additional picture header bits syntax element, when present, in the picture_header( ) syntax structure.

[0103] When additional picture header bits is present, its length, in bits, is picture header size * 8 - NumPhBitsAtThisPoint.

[0104] The value of NumPhBitsAtThisPoint shall be less than or equal to picture header size * 8. In codestreams conforming to this version of this standard, the value of picture header size * 8 - NumPhBitsAtThisPoint shall be less than 8. Decoders shall allow the value of picture header size * 8 - NumPhBitsAtThisPoint to be greater than or equal to 8 and shall ignore the value of additional picture header bits, when present.

[0105] Note that additional picture header bits can contain bits that are all extension bits, are all byte alignment bits, or are extension bits followed by byte alignment bits.

5.2 Embodiment 2

[0106] This embodiment is for some of the items summarized above in Section 4. 5.2.1 (2.2) Specification of syntax functions and descriptors

[0107] The functions presented here are used in the syntactical description. These functions are expressed in terms of the value of a bitstream pointer that indicates the position of the next bit to be read by the decoding process from the bitstream.

[0108] read_bits( n ) reads the next n bits from the bitstream and advances the bitstream pointer by n bit positions. When n is equal to 0, read_bits( n ) is specified to return a value equal to 0 and to not advance the bitstream pointer.

[0109] read_bits_from_back( n ) reads the n bits from the end of a sub-stream in bitstream and move back the sub-stream bitstream pointer by n bit positions. When n is equal to 0, read_bits_from_back( n ) is specified to return a value equal to 0 and to not move the sub-stream bitstream pointer.

[0110] The following descriptors specify the parsing process of each syntax element:

- b(n): byte having any pattern of bit string of n bits. The parsing process for this descriptor is specified by the return value of the function read_bits( n ).

- b(8): byte having any pattern of bit string (8 bits). The parsing process for this descriptor is specified by the return value of the function read_bits( 8 ).

- f(n) : fixed-pattern bit string using n bits written (from left to right) with the left bit first. The parsing process for this descriptor is specified by the return value of the function read_bits( n ).

- i(n): signed integer using n bits. When n is “v” in the syntax table, the number of bits varies in a manner dependent on the value of other syntax elements. The parsing process for this descriptor is specified by the return value of the function read_bits( n ) interpreted as a two's complement integer representation with most significant bit written first.

- ub(n): unsigned integer using n bits. When n is ‘ V’ in the syntax table, the number of bits varies in a maimer dependent on the value of other syntax elements. The parsing process for this descriptor is specified by the return value of the function read_bits_from_back( n ) interpreted as a binary representation of an unsigned integer with most significant bit written first.

5.2.2. (6.3) Picture header

[oni] This sub-stream contains information about image height H, width W. latent space tiles location and sizes, control flags for each tool, scaling factors for primary and secondary' component, modelldx - learnable model index and displacement for rate control parameters (fi_Y f°^r primary and _uv for secondary component). 2.4.2.1 (6.3.1) Syntax table

2.4.2.3 (6.3.2) Picture header semantics

[0112] Following service information is signalled:

[0113] picturc hcader size is the number of bytes in the picture header excluding the first two-byte marker;

[0114] Alternatively: picture header size is ue(v)-coded, where ue(v) coding is the same as specified in H.266/WC, which the also the same as in H.264/AVC and H.265/HEVC.

[0115] img width plus 64 specifies width of an input picture (from 64 to 65599);

[0116] img height plus 64 specifies height of the input picture (from 64 to 65599);

[0117] When present, additional_picture_header_bit[ i ] could have any value.

[0118] Let the variable NumPhBitsAtThisPoint be the total number of bits for all the syntax elements starting from the picture header size syntax element up to and excluding the additional_picture_header_bit[ 0 ] syntax element, when present, in the picture_header( ) syntax structure. [0119] The value of NumPhBitsAtThisPoint shall be less than or equal to picture header size * 8. In codestreams conforming to this version of this standard, the value of picture header size * 8 - NumPhBitsAtThisPoint shall be less than 8. Decoders shall allow the value of picture header size * 8 - NumPhBitsAtThisPoint to be greater than or equal to 8 and shall ignore the values of all present instances of additional_picture_header_bit[ i ].

[0120] Note that instances of additional_picture_header_bit[ i ] can be all extension bits, be all byte alignment bits, or be extension bits followed by byte alignment bits.

5.3 Embodiment 3

[0121] This embodiment covers some of the items summarized above in Section 4.

5.3.1 (6.3) Picture header

[0122] This sub-stream contains information about image height H. width W, latent space tiles location and sizes, control flags for each tool, scaling factors for primary and secondary component, modelldx - learnable model index and displacement for rate control parameters (J3_Y for primary' and p_uv for secondary' component). 2.4.2.1 (6.3.1) Syntax table

2.4.2.3 (6.3.2) Picture header semantics

[0123] Following service information is signalled:

[0124] picture header size is the number of bytes in the picture header excluding the first two-byte marker;

[0125] Alternatively: picture header size is ue(v)-coded, where ue(v) coding is the same as specified in H.266/VVC, which the also the same as in H.264/AVC and H.265/HEVC.

[0126] img width plus 64 specifies width of an input picture (from 64 to 65599);

[0127] img height plus 64 specifies height of the input picture (from 64 to 65599);

[0128] ph extension num bits specifies the number of extension bits present in the picture header.

The value of ph extension num bits shall be less than picture header size * 8.

[0129] Alternatively: ph extension num bits is ue(v)-coded, where ue(v) coding is the same as specified in H.266/WC, which the also the same as in H.264/AVC and H.265/HEVC.

[0130] Alternatively: The presence of ph extension num bits is conditioned on a presence flag, e.g., named ph extension present flag.

[0131] Alternatively: The value of ph extension num bits shall be less than picture header size * 8 - NumPhBitsAtThisPoint, w here NumPhBitsAtThisPoint is similar in embodiment 1 or 2.

[0132] picture_header_extension_bit[ i ] could have any value.

[0133] In codcstrcams conforming to this version of this standard, the value of ph extension num bits shall be equal to 0. Decoders shall allow the value of ph extension num bits to be greater than 0, and shall ignore the values of all instances of picture_header_extension_bit[ i ], when present. 5.4 Embodiment 4

[0134] This embodiment is for some of the items summarized above in Section 4.

5.4.1 Specification of syntax functions and descriptors

[0135] The functions presented here are used in the syntactical description. These functions are expressed in terms of the value of a bitstream pointer that indicates the position of the next bit to be read by the decoding process from the bitstream.

[0136] read_bits( n ) reads the next n bits from the bitstream and advances the bitstream pointer by n bit positions. When n is equal to 0, read_bits( n ) is specified to return a value equal to 0 and to not advance the bitstream pointer.

[0137] read_bits_from_back( n ) reads the n bits from the end of a sub-stream in bitstream and move back the sub-stream bitstream pointer by n bit positions. When n is equal to 0, read_bits_from_back( n ) is specified to return a value equal to 0 and to not move the sub-stream bitstream pointer.

[0138] The following descriptors specify the parsing process of each syntax element:

- i(n): signed integer using n bits. When n is ‘W in the syntax table, the number of bits varies in a manner dependent on the value of other syntax elements. The parsing process for this descriptor is specified by the return value of the function rcad_bits( n ) interpreted as a two's complement integer representation with most significant bit written first.

- u(n): unsigned integer using n bits. When n is “v” in the syntax table, the number of bits varies in a manner dependent on the value of other syntax elements. The parsing process for this descriptor is specified by the return value of the function read bits( n ) interpreted as a binary representation of an unsigned integer with most significant bit written first.

- ub(n): unsigned integer using n bits. When n is “v” in the syntax table, the number of bits varies in a manner dependent on the value of other syntax elements. The parsing process for this descriptor is specified by the return value of the function read_bits_from_back( n ) interpreted as a binary representation of an unsigned integer with most significant bit written first.

- ue(v): unsigned integer O-th order Exp-Golomb-coded syntax element with the left bit first. The parsing process for this descriptor is the same as in H.266/WC, which the also the same as in H.264/AVC and H.265/HEVC. 5.4.2 General sub-stream syntax and semantics

[0139] ss marker specifies the marker of the sub-stream.

[0140] When ss marker is equal to PIH, ss_payload( ss marker ). i.e., ss_payload( PIH ), is the picture_header( ) syntax structure excluding the first two syntax elements, PIH and picture header size.

[0141] When ss marker is equal to TOH, ss_payload( ss marker ), i.e., ss_payload( TOH ), is the tools_header( ) syntax structure excluding the first two syntax elements, TOH and tools header size.

[0142] When ss marker is equal to SOZ, ss_payload( ss marker ), i.e., ss_payload( SOZ ), is the z_stream( ) syntax structure excluding the first two syntax elements, SOZ and z stream size.

[0143] When ss marker is equal to SOQ, ss_payload( ss marker ), i.e., ss_payload( SOQ ), is the q_stream( ) syntax structure excluding the first two syntax elements, SOQ and q_stream_size.

[0144] When ss marker is equal to SORp, ss_payload( ss marker ). i.e., ss_payload( SORp ), is the r_primary_stream( ) syntax structure excluding the first two syntax elements, SORp and r_primary_stream_size.

[0145] When ss marker is equal to SORs, ss_payload( ss marker ), i.e., ss_paydoad( SORs ), is the r_secondary_stream( ) syntax structure excluding the first two sy ntax elements, SORs and r_secondary_stream_size.

[0146] When ss marker is equal to a reserved marker value (e.g., in the range of 0xff84 to 0xff87, inclusive, or in the range of 0xff8c to 0xff8f, inclusive), the syntax of ss_payload( ss marker ) is unspecified in this version of the standard and may be specified in a future version of the standard.

[0147] ss size minusl plus 1 specifies the size, in bytes, of the sub-stream excluding the syntax element ss marker. The value of ss size minusl shall be in the range of 0 to 31, inclusive.

[0148] ss alignment zero bit shall be equal to 0.

[0149] When present, additional_ss_bit[ i ] could have any value. [0150] Let the variable NumPhBitsAtThisPoint be the total number of bits for all the syntax elements starting from the ss size minusl syntax element up to and excluding the additional_ss_bit[ 0 ] syntax element, when present, in the sub_stream( ) syntax structure.

[0151] The value of NumPhBitsAtThisPoint shall be less than or equal to ( ss size minusl + 1 ) * 8. In codestreams conforming to this version of this standard, the value of ( ss size minusl + 1 ) - NumPhBitsAtThisPoint shall be less than 8. Decoders shall allow the value of ( ss size minusl + 1 ) * 8 - NumPhBitsAtThisPoint to be greater than or equal to 8 and shall ignore the values of all present instances of additional_ss_header_bit[ i ].

[0152] Note that instances of additional_ss_bit[ i ] can be all extension bits, be all byte alignment bits, or be extension bits followed by byte alignment bits.

5.4 Embodiment 5

[0153] This embodiment covers some of the items summarized above in Section 4.

5.5.1. (2.2) Specification of syntax functions and descriptors

[0154] The functions presented here are used in the syntactical description. These functions are expressed in terms of the value of a bitstream pointer that indicates the position of the next bit to be read by’ the decoding process from the bitstream.

[0155] read_bits( n ) reads the next n bits from the bitstream and advances the bitstream pointer by n bit positions. When n is equal to 0, read_bits( n ) is specified to return a value equal to 0 and to not advance the bitstream pointer.

[0156] read_bits_from_back( n ) reads the n bits from the end of a sub-stream in bitstream and move back the sub-stream bitstream pointer by n bit positions. When n is equal to 0, read_bits_from_back( n ) is specified to return a value equal to 0 and to not move the sub-stream bitstream pointer.

[0157] The following descriptors specify the parsing process of each syntax element:

- u(n): unsigned integer using n bits. When n is “v” in the sy ntax table, the number of bits varies in a manner dependent on the value of other syntax elements. The parsing process for this descriptor is specified by the return value of the function read_bits( n ) interpreted as a binary representation of an unsigned integer with most significant bit written first.

- ue(v): unsigned integer O-th order Exp-Golomb-coded syntax element with the left bit first. The parsing process for this descriptor is the same as in H.266/WC, which the also the same as in H.264/AVC and H.265/HEVC.

5.5.2. (6.3) Picture header

[0158] This sub-stream contains information about image height H, width W. latent space tiles location and sizes, control flags for each tool, scaling factors for primary and secondary component, modelldx - learnable model index and displacement for rate control parameters ( ?_y for primary and p_uv for secondary component).

2.4.2.1 (6.3.1) Syntax table

2.4.2.3 (6.3.2) Picture header semantics

[0159] Following service information is signalled:

[0160] picture header size is the number of bytes in the picture header excluding the first two-byte marker, picture header size, and all instances of ph alignment zero bit;

[0161] img width plus 64 specifies width of an input picture (from 64 to 65599);

[0162] img height plus 64 specifics height of the input picture (from 64 to 65599);

[0163] [0164] When present, additional_picture_header_bit[ i ] could have any value.

[0165] Let the variable NumPhBitsAtThisPoint be the total number of bits for all the syntax elements starting from the first syntax clement after all the byte alignment bits, if any, that immediately follow the picture header size syntax element, up to and excluding the additional_picture_header_bit[ 0 ] syntax element, when present, in the picture_header( ) syntax structure (i.e., the total number of bits for all the syntax elements starting from the first syntax element following the last instance of ph aligmnent zero bit, up to and excluding the additional_picture_header_bit[ 0 ] syntax element, when present, in the picture_header( ) syntax structure).

[0166] The value of NumPhBitsAtThisPoint shall be less than or equal to picture header size * 8. In codestreams conforming to this version of this standard, the value of picture header size * 8 - NumPhBitsAtThisPoint shall be less than 8. Decoders shall allow the value of picture header size * 8 - NumPhBitsAtThisPoint to be greater than or equal to 8 and shall ignore the values of all present instances of additional_picture_header_bit| i ].

[0167] Note that instances of additional_picture_header_bit[ i ] can be extension bits only, byte alignment bits only, or extension bits followed by byte alignment bits.

[0168] FIG. 1 is a block diagram showing an example video processing system 4000 in which various techniques disclosed herein may be implemented. Various implementations may include some or all of the components of the system 4000. The system 4000 may include input 4002 for receiving video content. The video content may be received in a raw or uncompressed format, e.g., 8 or 10 bit multi-component pixel values, or may be in a compressed or encoded format. The input 4002 max' represent a network interface, a peripheral bus interface, or a storage interface. Examples of network interface include wired interfaces such as Ethernet, passive optical network (PON), etc. and wireless interfaces such as wireless fidelity (Wi-Fi) or cellular interfaces.

[0169] The system 4000 may include a coding component 4004 that may implement the various coding or encoding methods described in the present disclosure. The coding component 4004 may reduce the average bitrate of video from the input 4002 to the output of the coding component 4004 to produce a coded representation of the video. The coding teclmiques are therefore sometimes called video compression or video transcoding techniques. The output of the coding component 4004 may be either stored, or transmitted via a communication connected, as represented by the component 4006. The stored or communicated bitstream (or coded) representation of the video received at the input 4002 may be used by a component 4008 for generating pixel values or displayable video that is sent to a display interface 4010. The process of generating user- viewable video from the bitstream representation is sometimes called video decompression. Furthermore, while certain video processing operations are referred to as ’‘coding” operations or tools, it will be appreciated that the coding tools or operations are used at an encoder and corresponding decoding tools or operations that reverse the results of the coding will be performed by a decoder.

[0170] Examples of a peripheral bus interface or a display interface may include universal serial bus (USB) or high definition multimedia interface (HDMI) or Displayport, and so on. Examples of storage interfaces include serial advanced technology attachment (SATA), peripheral component interconnect (PCI), integrated drive electronics (IDE) interface, and the like. The techniques described in the present disclosure may be embodied in various electronic devices such as mobile phones, laptops, smartphones or other devices that are capable of performing digital data processing and/or video display.

[0171] FIG. 2 is a block diagram of an example video processing apparatus 4100. The apparatus 4100 may be used to implement one or more of the methods described herein. The apparatus 4100 may be embodied in a smartphone, tablet, computer, Internet of Things (loT) receiver, and so on. The apparatus 4100 may include one or more processors 4102, one or more memories 4104 and video processing circuitry 4106. The processor(s) 4102 may be configured to implement one or more methods described in the present disclosure. The memory (memories) 4104 may be used for storing data and code used for implementing the methods and techniques described herein. The video processing circuitry 4106 may be used to implement, in hardware circuitry, some teclmiques described in the present disclosure. In some embodiments, the video processing circuitry 4106 may be at least partly included in the processor 4102. e.g., a graphics co-processor.

[0172] FIG. 3 is a flowchart for an example method 4200 of video processing. The method 4200 determines that a Joint Photographic Experts Group (JPEG) Artificial Intelligence (Al) sub-stream includes a sub-stream marker identifier (ID) syntax element, a sub-stream size syntax element, and sub-stream payload data; at step 4202. A conversion between a visual media data and the JPEG Al sub-stream is performed based on the determination at step 4204. The conversion may include encoding at an encoder, decoding at a decoder, or combinations thereof.

[0173] It should be noted that the method 4200 can be implemented in an apparatus for processing video data comprising a processor and a non-transitory memory with instructions thereon, such as video encoder 4400, video decoder 4500, and/or encoder 4600. In such a case, the instructions upon execution by the processor, cause the processor to perform the method 4200. Further, the method 4200 can be performed by a non-transitory computer readable medium comprising a computer program product for use by a video coding device. The computer program product comprises computer executable instructions stored on the non-transitory computer readable medium such that when executed by a processor cause the video coding device to perform the method 4200.

[0174] FIG. 4 is a block diagram that illustrates an example video coding system 4300 that may utilize the techniques of this disclosure. The video coding system 4300 may include a source device 4310 and a destination device 4320. Source device 4310 generates encoded video data which max’ be referred to as a video encoding device. Destination device 4320 may decode the encoded video data generated by source device 4310 which may be referred to as a video decoding device.

[0175] Source device 4310 may include a video source 4312. a video encoder 4314, and an input/output (I/O) interface 4316. Video source 4312 may include a source such as a video capture device, an interface to receive video data from a video content provider, and/or a computer graphics system for generating video data, or a combination of such sources. The video data may comprise one or more pictures. Video encoder 4314 encodes the video data from video source 4312 to generate a bitstream. The bitstream may include a sequence of bits that form a coded representation of the video data. The bitstream may include coded pictures and associated data. The coded picture is a coded representation of a picture. The associated data may include sequence parameter sets, picture parameter sets, and other syntax structures. I/O interface 4316 may include a modulator/demodulator (modem) and/or a transmitter. The encoded video data may be transmitted directly to destination device 4320 via I/O interface 4316 through network 4330. The encoded video data may also be stored onto a storage mcdium/scrver 4340 for access by destination device 4320.

[0176] Destination device 4320 may include an I/O interface 4326, a video decoder 4324, and a display device 4322. I/O interface 4326 may include a receiver and/or a modem. I/O interface 4326 max' acquire encoded video data from the source device 4310 or the storage medium/ server 4340. Video decoder 4324 may decode the encoded video data. Display device 4322 may display the decoded video data to a user. Display device 4322 may be integrated with the destination device 4320, or may be external to destination device 4320, which can be configmed to interface with an external display device.

[0177] Video encoder 4314 and video decoder 4324 may operate according to a video compression standard, such as the High Efficiency Video Coding (HEVC) standard, Versatile Video Coding (WC) standard and other current and/or further standards.

[0178] FIG. 5 is a block diagram illustrating an example of video encoder 4400, which may be video encoder 4314 in the system 4300 illustrated in FIG. 4. Video encoder 4400 may be configmed to perform any or all of the techniques of this disclosme. The video encoder 4400 includes a plurality of functional components. The teclmiques described in this disclosme may be shared among the various components of video encoder 4400. In some examples, a processor may be configmed to perform any or all of the techniques described in this disclosme. [0179] The functional components of video encoder 4400 may include a partition unit 4401, a prediction unit 4402 which may include a mode select unit 4403, a motion estimation unit 4404, a motion compensation unit 4405, an intra prediction unit 4406, a residual generation unit 4407, a transform processing unit 4408, a quantization unit 4409, an inverse quantization unit 4410, an inverse transform unit 4411, a reconstruction unit 4412, a buffer 4413, and an entropy encoding unit 4414.

[0180] In other examples, video encoder 4400 may’ include more, fewer, or different functional components. In an example, prediction unit 4402 may include an intra block copy (IBC) unit. The IBC unit may perform prediction in an IBC mode in which at least one reference pictme is a pictme where the current video block is located.

[0181] Furthermore, some components, such as motion estimation unit 4404 and motion compensation unit 4405 may be highly integrated, but are represented in the example of video encoder 4400 separately for purposes of explanation.

[0182] Partition unit 4401 may partition a picture into one or more video blocks. Video encoder 4400 and video decoder 4500 may support various video block sizes.

[0183] Mode select unit 4403 may select one of the coding modes, intra or inter, e.g., based on error results, and provide the resulting intra or inter coded block to a residual generation unit 4407 to generate residual block data and to a reconstruction unit 4412 to reconstruct the encoded block for use as a reference picture. In some examples, mode select unit 4403 may select a combination of intra and inter prediction (CIIP) mode in which the prediction is based on an inter prediction signal and an intra prediction signal. Mode select unit 4403 may also select a resolution for a motion vector (e.g., a sub-pixel or integer pixel precision) for the block in the case of inter prediction.

[0184] To perform inter prediction on a current video block, motion estimation unit 4404 may generate motion information for the current video block by comparing one or more reference frames from buffer 4413 to the current video block. Motion compensation unit 4405 may determine a predicted video block for the current video block based on the motion information and decoded samples of pictures from buffer 4413 other than the picture associated with the current video block.

[0185] Motion estimation unit 4404 and motion compensation unit 4405 may perform different operations for a current video block, for example, depending on whether the current video block is in an I slice, a P slice, or a B slice.

[0186] In some examples, motion estimation unit 4404 may perform uni-directional prediction for the current video block, and motion estimation unit 4404 may search reference pictures of list 0 or list 1 for a reference video block for the current video block. Motion estimation unit 4404 may then generate a reference index that indicates the reference picture in list 0 or list 1 that contains the reference video block and a motion vector that indicates a spatial displacement between the current video block and the reference video block. Motion estimation unit 4404 may output the reference index, a prediction direction indicator, and the motion vector as the motion information of the current video block. Motion compensation unit 4405 may generate the predicted video block of the current block based on the reference video block indicated by the motion information of the current video block.

[0187] In other examples, motion estimation unit 4404 may perform bi-directional prediction for the current video block, motion estimation unit 4404 may search the reference pictures in list 0 for a reference video block for the current video block and may also search the reference pictures in list 1 for another reference video block for the current video block. Motion estimation unit 4404 may then generate reference indexes that indicate the reference pictures in list 0 and list 1 containing the reference video blocks and motion vectors that indicate spatial displacements between the reference video blocks and the current video block. Motion estimation unit 4404 may output the reference indexes and the motion vectors of the current video block as the motion information of the current video block. Motion compensation unit 4405 may generate the predicted video block of the current video block based on the reference video blocks indicated by the motion information of the current video block.

[0188] In some examples, motion estimation unit 4404 may output a full set of motion information for decoding processing of a decoder. In some examples, motion estimation unit 4404 may not output a full set of motion information for the current video. Rather, motion estimation unit 4404 may signal the motion information of the current video block with reference to the motion information of another video block. For example, motion estimation unit 4404 may determine that the motion information of the current video block is sufficiently similar to the motion information of a neighboring video block.

[0189] In one example, motion estimation unit 4404 may indicate, in a syntax structure associated with the current video block, a value that indicates to the video decoder 4500 that the current video block has the same motion information as another video block.

[0190] In another example, motion estimation unit 4404 may identify, in a syntax structure associated with the current video block, another video block and a motion vector difference (MVD). The motion vector difference indicates a difference between the motion vector of the current video block and the motion vector of the indicated video block. The video decoder 4500 may use the motion vector of the indicated video block and the motion vector difference to determine the motion vector of the current video block.

[0191] As discussed above, video encoder 4400 may predictively signal the motion vector. Two examples of predictive signaling techniques that may' be implemented by^r video encoder 4400 include advanced motion vector prediction (AMVP) and merge mode signaling.

[0192] Intra prediction unit 4406 may perform intra prediction on the current video block. When intra prediction unit 4406 performs intra prediction on the current video block, intra prediction unit 4406 may generate prediction data for the current video block based on decoded samples of other video blocks in the same picture. The prediction data for the current video block may include a predicted video block and various syntax elements.

[0193] Residual generation unit 4407 may generate residual data for the current video block by subtracting the predicted video block(s) of the current video block from the current video block. The residual data of the current video block may include residual video blocks that correspond to different sample components of the samples in the current video block.

[0194] In other examples, there may be no residual data for the current video block for the current video block, for example in a skip mode, and residual generation unit 4407 may not perform the subtracting operation.

[0195] Transfonn processing unit 4408 may generate one or more transform coefficient video blocks for the current video block by applying one or more transforms to a residual video block associated with the current video block.

[0196] After transform processing unit 4408 generates a transform coefficient video block associated with the current video block, quantization unit 4409 may' quantize the transform coefficient video block associated with the current video block based on one or more quantization parameter (QP) values associated with the current video block.

[0197] Inverse quantization unit 4410 and inverse transfonn unit 4411 may apply inverse quantization and inverse transfonns to the transfonn coefficient video block, respectively, to reconstruct a residual video block from the transform coefficient video block. Reconstruction unit 4412 may add the reconstructed residual video block to corresponding samples from one or more predicted video blocks generated by the prediction unit 4402 to produce a reconstructed video block associated with the current block for storage in the buffer 4413. [0198] After reconstruction unit 4412 reconstructs the video block, the loop filtering operation may be performed to reduce video blocking artifacts in the video block.

[0199] Entropy encoding unit 4414 max’ receive data from other functional components of the video encoder 4400. When entropy encoding unit 4414 receives the data, entropy encoding unit 4414 may perform one or more entropy encoding operations to generate entropy encoded data and output a bitstream that includes the entropy encoded data.

[0200] FIG. 6 is a block diagram illustrating an example of video decoder 4500 which may be video decoder 4324 in the system 4300 illustrated in FIG. 4. The video decoder 4500 may be configured to perform any or all of the techniques of this disclosure. In the example shown, the video decoder 4500 includes a plurality of functional components. The techniques described in this disclosure may be shared among the various components of the video decoder 4500. In some examples, a processor may be configured to perform any or all of the techniques described in this disclosure.

[0201] In the example shown, video decoder 4500 includes an entropy decoding unit 4501, a motion compensation unit 4502, an intra prediction unit 4503, an inverse quantization unit 4504, an inverse transformation unit 4505, a reconstruction unit 4506, and a buffer 4507. Video decoder 4500 may, in some examples, perform a decoding pass generally reciprocal to the encoding pass described with respect to video encoder 4400.

[0202] Entropy decoding unit 4501 may retrieve an encoded bitstream. The encoded bitstream may include entropy coded video data (e.g., encoded blocks of video data). Entropy decoding unit 4501 may decode the entropy coded video data, and from the entropy decoded video data, motion compensation unit 4502 may determine motion information including motion vectors, motion vector precision, reference picture list indexes, and other motion information. Motion compensation unit 4502 may, for example, determine such information by performing the AMVP and merge mode.

[0203] Motion compensation unit 4502 may produce motion compensated blocks, possibly performing interpolation based on interpolation filters. Identifiers for interpolation filters to be used with sub-pixel precision may be included in the syntax elements.

[0204] Motion compensation unit 4502 may use interpolation filters as used by video encoder 4400 dining encoding of the video block to calculate interpolated values for sub-integer pixels of a reference block. Motion compensation unit 4502 may determine the interpolation filters used by video encoder 4400 according to received syntax information and use the interpolation filters to produce predictive blocks.

[0205] Motion compensation unit 4502 may use some of the syntax information to determine sizes of blocks used to encode frame(s) and/or slice(s) of the encoded video sequence, partition information that describes how each macroblock of a picture of the encoded video sequence is partitioned, modes indicating how each partition is encoded, one or more reference frames (and reference frame lists) for each inter coded block, and other information to decode the encoded video sequence. [0206] Intra prediction unit 4503 may use intra prediction modes for example received in the bitstream to form a prediction block from spatially adjacent blocks. Inverse quantization unit 4504 inverse quantizes, i.e., dequantizes, the quantized video block coefficients provided in the bitstream and decoded by entropy decoding unit 4501. Inverse transform unit 4505 applies an inverse transform.

[0207] Reconstruction unit 4506 may sum the residual blocks with the corresponding prediction blocks generated by motion compensation unit 4502 or intra prediction unit 4503 to form decoded blocks. If desired, a deblocking filter may also be applied to filter the decoded blocks in order to remove blockiness artifacts. The decoded video blocks are then stored in buffer 4507, which provides reference blocks for subsequent motion compensation/intra prediction and also produces decoded video for presentation on a display device.

[0208] FIG. 7 is a schematic diagram of an example encoder 4600. The encoder 4600 is suitable for implementing the techniques of WC. The encoder 4600 includes three in-loop filters, namely a deblocking filter (DF) 4602, a sample adaptive offset (SAG) 4604, and an adaptive loop filter (ALF) 4606. Unlike the DF 4602, which uses predefined filters, the SAG 4604 and the ALF 4606 utilize the original samples of the current picture to reduce the mean square errors between the original samples and the reconstructed samples by adding an offset and by applying a finite impulse response (FIR) filter, respectively’, with coded side information signaling the offsets and filter coefficients. The ALF 4606 is located at the last processing stage of each picture and can be regarded as a tool trying to catch and fix artifacts created by the previous stages.

[0209] The encoder 4600 further includes an intra prediction component 4608 and a motion estimation/compensation (ME/MC) component 4610 configured to receive input video. The intra prediction component 4608 is configured to perform intra prediction, while the ME/MC component 4610 is configured to utilize reference pictures obtained from a reference picture buffer 4612 to perform inter prediction. Residual blocks from inter prediction or intra prediction are fed into a transform (T) component 4614 and a quantization (Q) component 4616 to generate quantized residual transform coefficients, which are fed into an entropy coding component 4618. The entropy coding component 4618 entropy codes the prediction results and the quantized transform coefficients and transmits the same toward a video decoder (not shown). Quantization components output from the quantization component 4616 may be fed into an inverse quantization (IQ) components 4620, an inverse transform component 4622, and a reconstruction (REC) component 4624. The REC component 4624 is able to output images to the DF 4602, the SAG 4604, and the ALF 4606 for filtering prior to those images being stored in the reference picture buffer 4612.

[0210] A listing of solutions preferred by some examples is provided next.

[0211] The following solutions show examples of techniques discussed herein.

[0212] 1. A method for processing media data comprising: determining a coded image of a Joint

Photographic Experts Group (JPEG) Artificial Intelligence (Al) sub-stream, wherein the JPEG Al substream comprises a sub-strcam marker, a sub-strcam size syntax element, and a sub-strcam payload: and performing a conversion between a visual media data and the JPEG Al sub-stream based on the sub-stream payload. [0213] 2. The method of solution 1 , wherein the sub-stream marker is included in an X-bit marker syntax element, where X is 16.

[0214] 3. The method of any of solutions 1-2, wherein the sub-stream size syntax clement indicates a size of the sub-stream payload in bytes or bits, where the sub-stream payload is the sub-stream excluding the sub-stream marker or the sub-stream excluding the sub-stream marker and the size.

[0215] 4. The method of any of solutions 1-3, wherein the sub-stream size syntax element is u(N)-coded, where N is 8. 16, 24, or 32, or wherein the sub-stream size syntax element is ue(v)-coded.

[0216] 5. The method of any of solutions 1 -4, wherein the sub-stream payload excludes the sub-stream size syntax element when the sub-stream size syntax element is considered as part of the sub-stream payload.

[0217] 6. The method of any of solutions 1-5, wherein the JPEG Al substream further comprises data extension bits allowing for adding more data with specific syntax and semantics to the sub-stream, or wherein the number of data extension bits is signalled in the sub-stream, immediately before the data extension bits, to control the presence and the number of data extension bits.

[0218] 7. The method of any of solutions 1-6, wherein the JPEG Al substream further comprises byte alignment bits, which ensures that the total number of bits in the sub-stream is an integer multiple of 8.

[0219] 8. The method of any of solutions 1-7, wherein a presence of the data extension bits and the presence of the byte alignment bits are collectively controlled by one condition and collectively represented by one syntax element or instances of one syntax element.

[0220] 9. The method of any of solutions 1-8, wherein the condition is whether the number of bits in the sub-stream is less than that indicated by the sub-stream size syntax element.

[0221] 10. The method of any of solutions 1-9. wherein the JPEG Al sub-stream is one of a picture header sub-stream, a tools header sub-stream, a rendering information sub-stream, a quality map sub-stream, a hyper tensor sub-stream, a primary residual sub-stream, a secondary residual sub-stream, or a reserved type of sub-stream.

[0222] 11. The method of any of solutions 1-10, wherein when the sub-stream is a picture header sub-stream, the marker syntax element is a PIH syntax element, the sub-stream size syntax element is a picture header size, and the syntax element that collectively⁷ represents the data extension bits and the byte alignment bits is an additional_picture_header_bits syntax element.

[0223] 12. The method of any of solutions 1-11, wherein the additional_picture_header_bits syntax element is only present when picture header size * 8 is greater than NumPhBitsAtThisPoint, or wherein NumPhBitsAtThisPoint is the total number of bits for all the syntax elements starting from the picturc hcadcr sizc syntax element up to and excluding the additional_picture header bits syntax element, when present, in the picture_header( ) syntax structure, or wherein when additional_picture_header_bits is present, its length, in bits, is picture header size * 8 - NumPhBitsAtThisPoint, or wherein the value of NumPhBitsAtThisPoint shall be less than or equal to picture header size * 8, or wherein in conforming codestreams, the value of picturc hcadcr sizc * 8 - NumPhBitsAtThisPoint shall be less than 8, or wherein decoders shall allow the value of picture header size * 8 - NumPhBitsAtThisPoint to be greater than or equal to 8 and shall ignore the value of additional_picture_header_bits when present, or wherein additional_picture_header_bits can contain bits that are all extension bits, are all byte alignment bits, or are extension bits followed by byte alignment bits.

[0224] 13. The method of any of solutions 1-12, wherein when the sub-stream is the picture header substream, the marker syntax element is the PIH syntax element, the sub-stream size syntax element is the picture header size, and the syntax element whose instances that collectively represent the optionally’ present data extension bits and the optionally present byte alignment bits is the additional_picture_header_bit[ i ] syntax element.

[0225] 14. The method of any of solutions 1-13. wherein the additional picture header bit[ i ] syntax element is only present when picture header size * 8 is greater than NumPhBitsAtThisPoint, or wherein NumPhBitsAtThisPoint is the total number of bits for all the syntax elements starting from the picture header size syntax element up to and excluding the additional_picture_header_bit[ 0 ] syntax element when present in the picture_header( ) syntax structure, or wherein the number of present instances of the additional_picture_licader_bit| i ] syntax element is equal to picture header size * 8 - NumPhBitsAtThisPoint, or wherein the value of NumPhBitsAtThisPoint shall be less than or equal to picture hcader size * 8, or wherein in conforming codestreams the value of picture header size * 8 - NumPhBitsAtThisPoint shall be less than 8, or wherein decoders shall allow the value of picture header size * 8 - NmnPhBitsAtThisPoint to be greater than or equal to 8 and shall ignore the values of all present instances of additional_picture_header_bit[ i ], or wherein instances of additional_picture_header_bit[ i ] can be all extension bits, be all byte aligmnent bits, or be extension bits followed by byte alignment bits.

[0226] 15. The method of any of solutions 1-14, wherein the conversion includes encoding the visual media data into the JPEG Al sub-stream.

[0227] 16. The method of any of solutions 1-14, wherein the conversion includes decoding the visual media data from the JPEG Al sub-stream.

[0228] 17. An apparatus for processing video data comprising: a processor; and a non-transitory memory’ with instructions thereon, wherein the instructions upon execution by the processor, cause the processor to perform the method of any of solutions 1-16.

[0229] 18. A non-transitory computer readable medium comprising a computer program product for use by a video coding device, the computer program product comprising computer executable instructions stored on the non-transitory computer readable medium such that when executed by a processor cause the video coding device to perform the method of any of solutions 1-16.

[0230] 19. A non-transitory computer-readable recording medium storing a Joint Photographic Experts

Group (JPEG) Artificial Intelligence (Al) sub-stream of a video which is generated by a method performed by’ a video processing apparatus, wherein the method comprises: determining a coded image of a Joint Photographic Experts Group (JPEG) Artificial Intelligence (Al) sub-stream, wherein the JPEG Al substream comprises a sub- stream marker, a sub-stream size syntax element, and a sub-stream payload; and generating the JPEG Al sub-stream based on the determining.

[0231] 20. A method for storing bitstream of a video comprising: determining a coded image of a Joint

Photographic Experts Group (JPEG) Artificial Intelligence (Al) sub-stream, wherein the JPEG Al substream comprises a sub-stream marker, a sub-stream size syntax element, and a sub-stream payload; generating the JPEG Al sub-stream based on the determining; and storing the JPEG Al sub-stream in a non-transitory computer-readable recording medium.

[0232] 21. A method, apparatus, or system described in the present disclosure.

[0233] In the solutions described herein, an encoder may conform to the format rule by producing a coded representation according to the format rule. In the solutions described herein, a decoder may use the format rule to parse syntax elements in the coded representation with the knowledge of presence and absence of syntax elements according to the format rule to produce decoded video.

[0234] In the present disclosure, the term “video processing'’ may refer to video encoding, video decoding, video compression or video decompression. For example, video compression algorithms may be applied during conversion from pixel representation of a video to a corresponding bitstream representation or vice versa. The bitstream representation of a current video block may, for example, correspond to bits that are either co-located or spread in different places within the bitstream, as is defined by the syntax. For example, a macroblock may be encoded in terms of transformed and coded error residual values and also using bits in headers and other fields in the bitstream. Furthermore, dining conversion, a decoder may parse a bitstream with the knowledge that some fields may be present, or absent, based on the determination, as is described in the above solutions. Similarly, an encoder may determine that certain syntax fields are or are not to be included and generate the coded representation accordingly by including or excluding the syntax fields from the coded representation.

[0235] The disclosed and other solutions, examples, embodiments, modules and the functional operations described in this disclosure can be implemented in digital electronic circuitry, or in computer software, firmware, or hardware, including the structures disclosed in this disclosure and their structural equivalents, or in combinations of one or more of them. The disclosed and other embodiments can be implemented as one or more computer program products, i.e., one or more modules of computer program instructions encoded on a computer readable medium for execution by, or to control the operation of, data processing apparatus. The computer readable medium can be a machine-readable storage device, a machine-readable storage substrate, a memory device, a composition of matter effecting a machine-readable propagated signal, or a combination of one or more them. The term “data processing apparatus” encompasses all apparatus, devices, and machines for processing data, including by way of example a programmable processor, a computer, or multiple processors or computers. The apparatus can include, in addition to hardware, code that creates an execution environment for the computer program in question, e.g., code that constitutes processor firmware, a protocol stack, a database management system, an operating system, or a combination of one or more of them. A propagated signal is an artificially generated signal, e.g., a machine- generated electrical, optical, or electromagnetic signal, that is generated to encode information for transmission to suitable receiver apparatus.

[0236] A computer program (also known as a program, software, software application, script, or code) can be written in any form of programming language, including compiled or interpreted languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. A computer program does not necessarily correspond to a fde in a file system. A program can be stored in a portion of a fde that holds other programs or data (e.g.. one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub programs, or portions of code). A computer program can be deployed to be executed on one computer or on multiple computers that are located at one site or distributed across multiple sites and interconnected by a communication network.

[0237] The processes and logic flows described in this disclosure can be performed by one or more programmable processors executing one or more computer programs to perform functions by operating on input data and generating output. The processes and logic flows can also be performed by, and apparatus can also be implemented as, special purpose logic circuitry, e.g., a field programmable gate array (FPGA) or an application specific integrated circuit (ASIC).

[0238] Processors suitable for the execution of a computer program include, by way of example, both general and special purpose microprocessors, and any one or more processors of any kind of digital computer. Generally, a processor will receive instructions and data from a read only memory or a random-access memory or both. The essential elements of a computer are a processor for performing instructions and one or more memory devices for storing instructions and data. Generally, a computer will also include, or be operatively coupled to receive data from or transfer data to. or both, one or more mass storage devices for storing data, e.g., magnetic, magneto optical disks, or optical disks. However, a computer need not have such devices. Computer readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media and memory devices, including by way of example semiconductor mcmoty devices, e g., erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), and flash memory devices; magnetic disks, e.g., internal hard disks or removable disks; magneto optical disks; and compact disc read-only memory' (CD ROM) and Digital versatile disc-read only memory' (DVD-ROM) disks. The processor and the memory can be supplemented by', or incorporated in, special purpose logic circuitry .

[0239] While the present disclosure contains many specifics, these should not be construed as limitations on the scope of any subject matter or of what may be claimed, but rather as descriptions of features that may be specific to particular embodiments of particular techniques. Certain features that are described in the present disclosure in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately' or in any suitable subcombination. Moreover, although features may be described above as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a subcombination or variation of a subcombination.

[0240] Similarly, while operations are depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. Moreover, the separation of various system components in the embodiments described in the present disclosure should not be understood as requiring such separation in all embodiments.

[0241] Only a few implementations and examples are described and other implementations, enhancements and variations can be made based on what is described and illustrated in the present disclosure.

[0242] A first component is directly coupled to a second component when there are no intervening components, except for a line, a trace, or another medium between the first component and the second component. The first component is indirectly coupled to the second component when there are intervening components other than a line, a trace, or another medium between the first component and the second component. The term “coupled” and its variants include both directly coupled and indirectly coupled. The use of the term “about” means a range including ±10% of the subsequent number unless otherwise stated.

[0243] While several embodiments have been provided in the present disclosure, it should be understood that the disclosed systems and methods might be embodied in mam- other specific forms without departing from the spirit or scope of the present disclosure. The present examples are to be considered as illustrative and not restrictive, and the intention is not to be limited to the details given herein. For example, the various elements or components may be combined or integrated in another system or certain features may be omitted, or not implemented.

[0244] In addition, techniques, systems, subsystems, and methods described and illustrated in the various embodiments as discrete or separate may be combined or integrated with other systems, modules, techniques, or methods without departing from the scope of the present disclosure. Other items shown or discussed as coupled may be directly connected or may be indirectly coupled or communicating through some interface, device, or intermediate component whether electrically, mechanically, or otherwise. Other examples of changes, substitutions, and alterations are ascertainable by one skilled in the art and could be made without departing from the spirit and scope disclosed herein.

Claims

CLAIMS What is claimed is:

1. A method for processing media data comprising: determining that a Joint Photographic Experts Group (JPEG) Artificial Intelligence (Al) sub-stream includes a sub-stream marker identifier (ID) syntax element, a sub-stream size syntax element, and sub-stream payload data; and performing a conversion between a visual media data and the JPEG Al sub-stream based on the determination.

2. The method of claim 1, wherein the sub-stream marker ID syntax element comprises X bits.

3. The method of claim 2, wherein X is equal to 16.

4. The method of any of claims 1-3, wherein the sub-stream size syntax element indicates a size of the substream payload in bytes.

5. The method of any of claims 1-3, wherein the sub-bitstream size syntax element indicates a size of the sub-bitstream payload in bits.

6. The method of any of claims 1-5, wherein the sub-stream payload data comprises the JPEG Al sub-stream excluding the sub-stream marker ID syntax element.

7. The method of any of claims 1-5, wherein the sub-stream payload data comprises the JPEG Al sub-stream excluding the sub-stream marker ID syntax element and the sub-stream size syntax element.

8. The method of any of claims 1 -5 , wherein the sub-stream payload data comprises the JPEG Al sub-stream excluding the sub-stream marker ID syntax element, the sub-stream size syntax element, and byte alignment bits immediately following the sub-stream size sy ntax element.

9. The method of any of claims 1-8, wherein the sub-stream size syntax element is coded as an unsigned integer using N bits (u(N)), where N is 8, 16, 24, or 32.

10. The method of any of claims 1-8, wherein the sub-stream size syntax element is coded as an unsigned exponential-Golomb-coded value of a variable number of bits (ue(v)).

11. The method of claim 10, wherein the sub-stream size syntax element specifies a size of the JPEG Al substream excluding the sub-stream marker ID syntax element, in bytes, minus 1.

12. The method of any of claims 1-11, wherein the JPEG Al sub-stream optionally includes byte alignment bits, and wherein the byte aligmnent bits ensure that a total number of bits in the JPEG Al sub-stream before the sub-stream payload data is an integer multiple of 8.

13. The method of any of claims 1-12, wherein the sub-strcam payload data excludes the sub-strcam size syntax element.

14. The method of any of claims 1-13, wherein the JPEG Al sub-stream optionally includes data extension bits, wherein the data extension bits permit versions of the JPEG Al standard after version 1 to add additional data with specific syntax and semantics to the JPEG Al sub-stream.

15. The method of any of claims 1-14, wherein a number of the data extension bits is included in the JPEG Al sub-stream, and wherein the number of data extension bits are configured to control a presence and the number of data extension bits.

16. The method of claim 1 , wherein the number of bits is included in the JPEG Al sub-stream immediately before the data extension bits.

17. The method of any of claims 1-16, wherein the byte alignment bits ensure that the total number of bits in the JPEG Al sub-stream is an integer multiple of 8.

18. The method of any of claims 1-17, wherein a presence of the data extension bits and the byte alignment bits in the JPEG Al sub-stream is collectively controlled by a single condition, and wherein the data extension bits and the byte alignment bits are collectively represented in the JPEG Al sub-stream by a single syntax element or instances of a single syntax element.

19. The method of claim 18, wherein the condition is whether a number of bits in the JPEG Al sub-stream is less than indicated by the sub-stream size syntax element.

20. The method of any of claims 1-19, wherein the JPEG Al sub-stream comprises one of a picture header sub-stream, a tools header sub-stream, a rendering information sub-stream, a quality map sub-stream, a hyper tensor sub-stream, a primary residual sub-stream, a secondary' residual sub-stream, or one of a plurality of reserved types of sub -streams.

21. The method of any of claims 1-20, wherein the sub-stream size syntax element is designated ss size minusl, and wherein a syntax element designated additional_ss_bit[ i ] collectively represents the byte alignment bits and the data extension bits optionally included in the JPEG Al sub-stream.

22. The method of any of claims 1-21, wherein the additional_ss_bit[ i ] is only present in the JPEG Al substream when the ss size minusl plus 1, multiplied by 8, is greater than a total number of bits for all syntax elements starting from the ss size minusl up to and excluding the additional_ss_bit[ 0 ], when present, in the JPEG Al sub-stream.

23. The method of claim 22, wherein the total number of bits for all syntax elements is a variable designated NumPhBitsAtThisPoint.

24. The method of any of claims 21-23, wherein a number of present instances of the additional ss bit[ i ] is equal to the ss size minusl plus 1. multiplied by 8. minus the NumPhBitsAtThisPoint.

25. The method of any of claims 21-24, wherein a value of the NumPhBitsAtThisPoint is less than or equal to the ss size minusl plus 1, multiplied by 8.

26. The method of any of claims 21-25, wherein a value of the ss size minusl plus 1, multiplied by 8, minus the NumPhBitsAtThisPoint is less than 8 in codestreams conforming to version 1 of the JPEG Al standard.

27. The method of any of claims 21-26, wherein a value of the ss size minusl plus 1, multiplied by 8, minus the NumPhBitsAtThisPoint is permitted by a decoder to be greater than or equal to 8, and wherein values of all present instances of the additional_ss_bit[ i ] are ignored by the decoder.

28. The method of any of claims 21-26, wherein instances of the additional_ss_bit[ i ] are extension bits only, byte alignment bits only, or extension bits followed by byte alignment bits.

29. The method of any of claims 1-28, wherein the conversion includes encoding the visual media data into the bitstream.

30. The method of any of claims 1-28, wherein the conversion includes decoding the visual media data from the bitstream.

31. An apparatus for processing video data comprising: a processor; and a non-transitor memory with instructions thereon, wherein the instructions upon execution by the processor, cause the processor to perform the method of any of claims 1 -30.

32. A non-transitory computer readable medium comprising a computer program product for use by a video coding device, the computer program product comprising computer executable instructions stored on the non- transitory computer readable medium such that when executed by a processor cause the video coding device to perform the method of any of claims 1-30.

33. A non-transitory computer-readable recording medium storing a bitstream of a video which is generated by a method performed by a video processing apparatus, wherein the method comprises: determining that a Joint Photographic Experts Group (JPEG) Artificial Intelligence (Al) sub-stream includes a sub-stream marker identifier (ID) syntax element, a sub-stream size syntax element, and sub-stream payload data; and generating the JPEG Al sub-stream based on the determination.

34. A method for storing bitstream of a video comprising: determining that a Joint Photographic Experts Group (JPEG) Artificial Intelligence (Al) sub-stream includes a sub-stream marker identifier (ID) syntax element, a sub-stream size syntax element, and sub-stream paydoad data; generating the JPEG Al sub-stream based on the determination; and storing the bitstream in a non-transitory computer-readable recording medium.

35. A method, apparatus, or system described in the present disclosure.