Signalling and storage of timed image sequences coded with JPEG ai in a media file

Abstract

A mechanism for processing video data is disclosed. The mechanism includes determining to specify a particular sample entry type for use by a motion Joint Photographic Experts Group Artificial Intelligence (JPEG AI) code stream. A conversion is performed between a visual media data and a bitstream based on the particular sample entry type specified as the motion JPEG AI code stream.

Description

P24012302799WO1; G24N08582W (4824-54002) Signalling And Storage Of Timed Image Sequences Coded With JPEG AI In A Media File CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This patent application claims the benefit of U.S. Patent Application No. 63 / 621,828 filed on January 17, 2024, and U.S. Patent Application No.63 / 655,822 filed on June 4, 2024, each of which is hereby incorporated by reference. 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 to specify aparticular sample entry type for use by a motion Joint Photographic Experts Group Artificial Intelligence (JPEG AI) code stream; and performing a conversion between a visual media data and a bitstream based on the particular sample entry type specified as the motion JPEG AI code stream.

[0005] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the particular sample entry type is referred to as a sample entry name.

[0006] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the particular sample entry type is referred to as a ‘jaim’.

[0007] Optionally, in any of the preceding aspects, another implementation of the aspect provides that asample entry of the particular sample entry type includes a configuration box.

[0008] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the configuration box contains information corresponding to a stream profile to which JPEG AI coded images carried in samples associated with the sample entry conform.

[0009] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the configuration box contains information corresponding to decoder profiles provided by JPEG AI coded images carried in samples associated with the sample entry.

[0010] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the configuration box contains information corresponding to a level to which JPEG AI coded images carried in samples associated with the sample entry conform.

[0011] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the configuration box contains information corresponding to a color format of output pictures resulting from decoding JPEG AI coded images carried in samples associated with the sample entry.P24012302799WO1; G24N08582W (4824-54002)

[0012] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the configuration box contains information corresponding to a bit depth of output pictures resulting from decoding JPEG AI coded images carried in samples associated with the sample entry.

[0013] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the configuration box contains information corresponding to a frame rate of a sequence of JPEG AI coded images carried in samples associated with the sample entry.

[0014] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the configuration box contains information corresponding to a bit rate of a sequence of JPEG AI coded images carried in samples associated with the sample entry.

[0015] Optionally, in any of the preceding aspects, another implementation of the aspect provides thatthe configuration box contains information corresponding to one or more of color sampling modes, scaling factors, a coded image color format, and a output image color format.

[0016] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the configuration box contains information corresponding to partitioning of a picture into regions.

[0017] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the regions comprise one or more of a number of region rows and a number of region columns.

[0018] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the configuration box contains information indicating whether each coded region is in its own substream.

[0019] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the configuration box contains information indicating whether partitioned regions are independent from each other.

[0020] 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.

[0021] 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.

[0022] 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 embodiments.

[0023] 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 disclosed embodiments.

[0024] 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 to specify a particular sample entry type for use by a motion Joint Photographic Experts Group Artificial Intelligence (JPEG AI) code stream; and generating a bitstream based on the particular sample entry type specified as the motion JPEG AI code stream.P24012302799WO1; G24N08582W (4824-54002)

[0025] A fifth aspect relates to a method for storing bitstream of a video comprising: determining to specify a particular sample entry type for use by a motion Joint Photographic Experts Group Artificial Intelligence (JPEG AI) code stream; generating a bitstream based on the determining; and storing the bitstream in a non-transitory computer-readable recording medium.

[0026] A sixth aspect relates to a method, apparatus, or system described in the present disclosure.

[0027] 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.

[0028] These and other features will be more clearly understood from the following detailed descriptiontaken in conjunction with the accompanying drawings and claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] 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.

[0030] FIG.1 is a diagram of an example codestream structure.

[0031] FIG.2 is a block diagram showing an example video processing system.

[0032] FIG.3 is a block diagram of an example video processing apparatus.

[0033] FIG.4 is a flowchart for an example method of video processing.

[0034] FIG.5 is a block diagram that illustrates an example video coding system.

[0035] FIG.6 is a block diagram that illustrates an example encoder.

[0036] FIG. 7 is a block diagram that illustrates an example decoder.

[0037] FIG.8 is a schematic diagram of an example encoder. DETAILED DESCRIPTION

[0038] 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.

[0039] Section headings are used in the present disclosure for ease of understanding and do not limit the applicability of techniques and embodiments disclosed in each section only to that section. Furthermore, H.266 terminology is used in some description only for ease of understanding and not for limiting scope of the disclosed techniques. As such, the techniques described herein are applicable to other video codec protocols and designs also. In the present disclosure, editing changes are shown to text by bold italics indicating cancelled text and bold indicating added text, with respect to the Versatile Video Coding (VVC) specification and / or the SEI messages for coded video bitstreams (VSEI) standard.P24012302799WO1; G24N08582W (4824-54002) 1. Initial discussion

[0040] This disclosure is related to Joint Photographic Experts Group Artificial Intelligence (JPEG AI) coded image file format. Specifically, this disclosure is related to signalling and storage of timed image sequences coded with JPEG AI in a media file, either based on the high efficiency image file format (HEIF), which is in turn based on the International Organization for Standardization (ISO) base media file format (ISOBMFF), or directly based on the ISOBMFF. The ideas may be applied individually or in various combinations, for images coded by any neural network (NN)-based codec, e.g., JPEG AI (i.e., ISO / International Electrotechnical Commission (IEC) 6048 1, Information technology — Learning-based image coding system (JPEG AI) — Part 1: Core coding system), and for any image file format, e.g., the JPEG AI image sequence file format or motion JPEG AI file format. 2. Further discussion 2.1 File format standards

[0041] Media streaming applications may be based on the Internet Protocol (IP), Transmission Control Protocol (TCP), and HyperText Transfer Protocol (HTTP) transport methods, and may rely on a file format such as the ISO base media file format (ISOBMFF) [1]. One such streaming system is dynamic adaptive streaming over HTTP (DASH)[2]. For using a video format with ISOBMFF and DASH, a file format specification specific to the video format, such as the Advanced Video Coding (AVC) file format and the High Efficiency Video Coding (HEVC) file format in [3], would be needed for encapsulation of the video content in ISOBMFF tracks and in DASH representations and segments. Information about the video bitstreams, e.g., the profile, tier, and level, and many others, may be exposed as file format level metadata and / or DASH media presentation description (MPD) for content selection purposes, e.g., for selection of appropriate media segments both for initialization at the beginning of a streaming session and for stream adaptation during the streaming session.

[0042] Similarly, for using an image format with ISOBMFF, a file format specification specific to the image format, such as the AVC image file format and the HEVC image file format in [4], may be used. 2.2. Neural network (NN)-based image and video coding

[0043] 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 network-based image compression algorithm achieves comparable rate-distortion (R-D) performance with Versatile Video Coding (VVC), 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.P24012302799WO1; G24N08582W (4824-54002) 2.2.1 Image / video compression

[0044] 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.

[0045] 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.

[0046] 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 two 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 / AVC and H.265 / 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 (VVC). The first version of VVC was released in July 2020. An average of 50% bitrate reduction is reported by VVC under the same visual quality compared with HEVC.

[0047] A number of researchers are working on neural network-based image coding used in neural network-based image / video compression. But the network 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.P24012302799WO1; G24N08582W (4824-54002) 2.2.2 Neural networks

[0048] 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, whilst processing such data has been a longstanding difficulty in the artificial intelligence field. 2.2.3. Neural networks for image and video compression

[0049] 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.

[0050] 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.

[0051] 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. 2.2.4. The JPEG AI image coding standard

[0052] At the time of writing, the JPEG AI image coding standard is an image coding standard that is being standardized by the JPEG Working Group (WG), which is WG 1 of ISO / IEC JTC 1 SC 29. The ISO / IEC number for the JPEG AI standard is ISO / IEC 6048. The latest JPEG AI draft specification is included in JPEG output document WG1N100660.

[0053] The design in the latest JPEG AI draft specification utilizes some NN-based image coding methods described mentioned above. Some of the features in the latest JPEG AI specification, together with a possible method for signalling of profiles and levels, are described or summarized below. The section numbers in the parentheses are the same as in the document WG1N100660. 2.2.4.1. (9.2) Code stream layout ...P24012302799WO1; G24N08582W (4824-54002)

[0054] The overall syntax structure of an image is: picture() { Descriptor SOC u(16)ws: Code assignment Symbol Description Mandatory / Optional 0ff80 SOC St t f d t M dt...P24012302799WO1; G24N08582W (4824-54002) 2.2.4.2. (9.3) Picture header

[0056] This sub-stream contains information about image height ^, width ^, latent space tiles location and sizes, control flags for each tool, scaling factors for primary and secondary component, ^^^^^^^^ – learnable model index and displacement for rate control parameters (^^for primary and ^^^for secondary component). 2.2.4.2.1 (9.3.1) Syntax table picture_header( ) { Descriptor PIH u(16)2.2.4.2.2. (9.3.1.2) Profile and level syntax profile_level() { Descriptor2.2.4.2.3. (9.3.2) Picture header semantics

[0057] Following service information is signalled: picture_header_size is the number of bytes in the picture header excluding the first two-byte marker; img_width plus 64 specifies width of an input picture (from 64 to 65600);P24012302799WO1; G24N08582W (4824-54002) img_height plus 64 specifies height of the input picture (from 64 to 65600); picture_format is a data format of the output picture (YUV420 = 0, YUV444 = 1, sRGB = 2, YUV422 = 3); bit_depth is a bit-depth the output picture (“0” corresponds to 8 and “1” corresponds to 10); ... stream_profile_idc indicates the stream profile to which the codestream conforms. num_decoder_profiles_minus1 plus 1 specifies the number of supported decoder profiles provided by the codestream. decoder_profile_idc[ i ] indicates the i-th supported decoder profiles provided by the codestream. level_idc indicates the level to which the codestream conforms. ... 2.2.5 The progressed draft JPEG AI image coding standard

[0058] A draft specification of the JPEG AI image coding standard is included in JPEG output document WG1N100864, an output from the 103rd JPEG meeting.

[0059] The design in the latest JPEG AI draft specification utilizes some NN-based image codingmethods described mentioned above. Some of the features in the latest JPEG AI specification, including signalling of profiles and levels, are described below. ... 1 Codestream structure and entropy coder 1.1 General

[0060] This annex specifies the codestream structure (sub-clause 11.2) and entropy decoder operations. Encoder shall produce stream compliant to the specified order of elements. 1.2 Codestream layout

[0061] The codestream is composed of start and end of stream markers, and multiple marker segments, which are parts of codestream started with a marker. Each maker segment has a byte aligned boundary. Marker and marker segments are: – SOC - start of codestream marker; – PIH - start of picture header marker segment followed by picture header substream (sub-clause 11.4);– SOZ - start of z-stream marker segment followed by substream of hyper tensor z, including ^̂ ^0^(“^^^^^^ ^^”) and ^^̂1^ (“^^^^^^ ^^^”) – SORp - start of residual stream for primary component marker segment followed by substream of primary component residual, which includes ^^̂0^ data (“^^^^^^ ^^”); – SORs - start of residual stream for secondary component marker segment followed by substream of secondary component residual, which includes ^̂^1^ data (“^^^^^^ ^^^”) ; – TOH - start of tools header marker segment followed by tools information substream (sub-clause 11.4.2); – RDI - start of rendering information marker segment followed by rendering information substream (sub- clause 11.8); – SOQ - start of quality map marker segment followed by substream (sub-clause 11.5.2); – UDI - start of used defined information marker segment followed by substream (sub-clause 11.7);P24012302799WO1; G24N08582W (4824-54002) – EOC - end of codestream marker.

[0062] FIG.1 is a diagram of an example layout of a codestream structure. Markers are shown as boxes. Each marker (except SOC – start and EOC – end of codestream) are followed by codestream segment. Each codestream segment starts with syntax element which specifies the size of the segment. With marker and codestream segment’s size, the start and the end of each codestream segment are identified. After parsing the number of bytes specified in the codestream segment’s size, parsing of this codestream segment is aborted. The order of codestream segments is shown in FIG. 1 as vertical line. The order restrictions are as follows: codestream starts with SOC, ends with EOC markers. Code segments shown in FIG.1 as boxes on both sides of the vertical line can be placed in a codestream in arbitrary order, but must be proceeded by PIH (Picture header) codestream segment. Some codestream segments are mandatory. They are shown on FIG. 1 as boxes the left side from the vertical line, which are connected to with a solid line. Optional codestream segments are shown on FIG.1 as boxes the right side from the vertical line, which are connected to with a dash line.

[0063] Codestream segments started with markers SOZ, SORr, SORp, SOQ are parsed with me-tANS entropy coder (sub-clause 11.5.4).

[0064] Each codestream starts with a 16-bit marker. All markers used in this specification and their interpretation are listed in the Table 1. Table 1 ^ Codestream markers. Code assignment Symbol Description Mandatory / OptionalP24012302799WO1; G24N08582W (4824-54002)

[0065] Markers with code assignment 0xff85..0xff87 are reserved for future use of this version of the standard. If any of the marker values 0xff85..0xff87 appears in the codestream then following codestream segment must be ignored. Markers with code assignment 0xff8d..0xff8f are reserved for future use in future versions of the standard. If any of the marker values 0xff8d..0xff8f appears in the codestream then decoding must be aborted, i.e., the decoder shall ignore the entire codestream. 1.3 Substream syntax 1.3.1 Substream syntax structure

[0066] A bitstream contains substreams. Each of them, including those associated with reserved markers, starts with a marker identifier (ID), the size of the substream and the payload data.

[0067] Except for the picture header substream, the syntax of all other substreams follows the syntax of the substream( ) syntax structure, wherein a byte_alignment( ) syntax structure exists immediately following the substream_size syntax element and also at the end of the substream.

[0068] The size of the substream enables discarding of substreams associated with reserved marker in future versions of the standard in case of decoding by legacy decoders. The decoders can read the marker ID and if it doesn’t support the marker, the decoder shall discard the remaining bytes of the substream as indicated by the size field. substream( ) { Descriptor marker id u(16)byte_alignment( ) { DescriptorP24012302799WO1; G24N08582W (4824-54002) substream_payload(marker_id) { Descriptor if ( marker_id == TOH ) {

[0069] marker_id is the marker identifier of the substream. Possible values are listed in the sub-clause 11.2.

[0070] substream_size is the size of the substream in bytes, excluding two bytes for marker and the size in bytes for substream_size itself.

[0071] alignment_zero_bit shall be equal to 0.1.4 Picture header 1.4.1 Picture header syntax

[0072] This marker segment contains information about image height ^, width ^, latent domain tiles location and sizes, control flags for each tool, scaling factors for primary and secondary component, learnable model index and displacement for rate control parameters (^^for primary and ^^^for secondary component).picture_header( ) { DescriptorP24012302799WO1; G24N08582W (4824-54002) for( i = 0; i <= num_decoder_profiles_minus1; i++ ) decoder_profile_idc[ i ] u(4)P24012302799WO1; G24N08582W (4824-54002) hyper_decode_overlap_in_latent_samples u(2) mcm_overlap_in_latent_samples u(4)P24012302799WO1; G24N08582W (4824-54002) synthesis_tile_size[comp] u(8) synthesis_tile_overlap[comp] u(5)

[0073] Following service information is signalled:

[0074] picture_header_size is the number of bytes in the picture header substream excluding the first two- byte marker, picture_header_size, and the byte_alignment( ) syntax structure.

[0075] stream_profile_idc indicates the stream profile to which the codestream conforms.

[0076] num_decoder_profiles_minus1 plus 1 specifies the number of supported decoder profilesprovided by the codestream.

[0077] decoder_profile_idc[ i ] indicates the i-th supported decoder profiles provided by the codestream. Variable decoderID is equal to decoder_profile_idc[ i ] which is an identifier for the synthesis transform network (sub-clause 10.3).

[0078] level_idc indicates the level to which the codestream conforms.

[0079] img_width_minus64 plus 64 specifies width of an input picture (from 64 to 65599). Variable W= img_width = img_width _minus64 + 64.

[0080] img_height_minus64 plus 64 specifies height of the input picture (from 64 to 65599). Variable H = img_height = img_height _minus64 + 64.

[0081] diff_display_img_width is a value ranging from 0 to 63;

[0082] display_image_width = img_width – diff_display_img_width

[0083] display_image_width specifies that pixels in the column 0 to column display_image_width - 1 of the decoded image are for display, and the pixels in the rest of the columns are not for display;

[0084] diff_display_img_height is a value ranging from 0 to 63;P24012302799WO1; G24N08582W (4824-54002)

[0085] display_image_height = img_height – diff_display_img_height

[0086] display_image_height specifies that pixels in the row 0 to row display_image_height - 1 of the decoded image are for display, and the pixels in the rest of the rows are not for display;

[0087] bit_depth_idc is the bit-depth the output picture (“0” corresponds to 8 and “1” corresponds to 10; other values are reserved);

[0088] s_ver_minus1 is one bit value which defines sver= 1 + s_ver_minus1; sveris a ratio between primary and secondary components height in output picture. Allowed values for sverare specified in Table 3. Usage of sveris specified in sub-clauses 5.3, 8.6, 8.7, 8.8.

[0089] s_hor_minus1 is a one bit value which defines shor =1+shor is a ratio between primary secondary components width in output picture. Allowed values for sverare specified in Table 3. Usage of sver is specified in sub-clauses 5.3, 8.6, 8.7, 8.8.

[0090] c_ver_minus1 is one bit value which defines cver = 1 + cver is a ratio between primary secondary components height in coded picture. Allowed values for cver are specified in Table 3:1^ sver^cver^2. Usage of cveris specified in the sub- , 8.6 and 10.3.is a one bit value which defines chor=1+ choris a ratio betweenwidth in coded picture. Allowed values for chorare specified in Table 3:1^ shor^chor^2. . Usage of choris specified in the sub-is a flag (false / true), independent_beta_uv equal to true indicates that thebeta displacement parameter for primary and secondary components are different. If independent_beta_uv equal to false then beta displacement parameter for primary and secondary components are the same.

[0093] beta_displacement_log_plus_2048[comp] minus 2048 is a parameter indicating a displacement between the rate control parameter beta selected by encoder for the comp component and the reference rate control parameter beta associated with the index of the used model (model_id syntax element). The displacement is in logarithmic scale. betaDisplacementLog[comp] should be in range -1069 to 702 inclusive, to preserve the performance of variable rate coding. betaDisplacementLog[comp] = clip(-1069,702, beta_displacement_log_plus_2048[comp] – 211)

[0094] NOTE – the reference rate control parameter beta (β), mentioned here, is the parameter used in the model training to control the ratio between the bitrate and distortion. The “model” here means the model associated with the index of the used model (model_id).

[0095] When syntax element beta_displacement_log_plus_2048[1] is not present (independent_beta_uv is equal to 0), betaDisplacementLog[1] = betaDisplacementLog[0]

[0096] model_id is an identificator of the pre-stored checkpoint with model’s weights, model_id = 0,1,2 or 3. Other values (i.e., from 4 to 15) are reserved for future extensions of the standard.

[0097] synthesis_tile_enable[comp] are enable flags for tiling of primary in synthesis transform (comp==0) and secondary (comp==1) components.

[0098] synthesis_tile_size[comp] are size of tiles in synthesis transform for primary (comp==0) andsecondary (comp==1) components counted in elements of latent tensor. The variablesP24012302799WO1; G24N08582W (4824-54002) SynthesisTransfromTileSize[0] = synthesis_tile_size[0] * 16. The variables SynthesisTransfromTileSize [1] = synthesis_tile_size[1] * 16

[0099] synthesis_tile_overlap[comp] are sizes of tiles in synthesis transform overlapping areas for primary (comp==0) and secondary (comp==1) components. If not present in the bitstream synthesis_tile_overlap[0]=0 and synthesis_tile_overlap[1]=0. The variables SynthesisTransfromTileOverlap [0] = synthesis_tile_overlap [0] * 16 The variables SynthesisTransfromTileOverlap [1] = inprediction are not partitioned.

[0101] num_ver_splits_minus1 plus 1 specifies the number of vertical splits of residual tensor and tensors in latent prediction and reconstruction process. When num_ver_splits_minus1 is not present, its value is inferred to be equal to 0.

[0102] The variable NumVerSubTensorSplits is derived to be equal to num_ver_splits_minus1 + 1.

[0103] The maximum and the minimum value of NumVerSubTensorSplits is constrained depending on the profile and the level to which the codestream conforms.

[0104] num_hor_splits_minus1 plus 1 specifies the number of horizontal splits. When num_hor_splits_minus1 is not present, its value is inferred to be equal to 0.

[0105] The variable NumHorSubTensorSplits is derived to be equal to num_hor_splits_minus1 + 1.

[0106] The maximum and the minimum value of NumHorSubTensorSplits is constrained depending on the profile and the level to which the codestream conforms.

[0107] mcm_overlap_in_latent_samples specifies the amount of overlap used in Multi-stage Context Modelling process in number of latent samples. The variable McmOverlap is set equal to mcm_overlap_in_latent_samples *2. If not present then set to 0.

[0108] hyper_decode_overlap_in_latent_samples specifies the amount of overlap used in Hyper decoding process in number of latent samples. The variable HyperDecoderOverlap is set equal to hyper_decode_overlap_in_latent_samples*2. If not present then set to 0.

[0109] region_residual_in_its_own_substream_flag equal to 1 specifies that the primary or secondary residual data for each region is in a substream. Residual substreams for multiple regions can be present in the codestream. region_residual_in_its_own_substream_flag equal to 0 specifies that there is only one substream for primary and only one substream for secondary residual data.

[0110] The variable VerSubTensorSize is set equal to floor(floor((img_height + 127) / 128) / NumHorResSplits)*128.

[0111] The variable HorSubTensorSize is set equal to floor(floor((img_width + 127) / 128) / NumVerResSplits)* 128.P24012302799WO1; G24N08582W (4824-54002)

[0112] The tensors RCVer [6][NumVerSubTensorSplits][3] and RCHor [6][NumHorSubTensorSplits][3] are set as follows:

[0113] For d = 0..5; For i = 0..NumHorSplits-1; ^RCVer[d][i][0] = i*VerSubTensorSize / 2d^RCVer [d][i][1]=(i==( NumVerSubTensorSplits –1))? hd: (i+1)*VerSubTensorSize / 2d^RCVer [d][i][2] = RCVer [d][i][1] – RCVer [d][i][0] For j = 0..NumVerSplits-1; ^RCHor [d][j][0] = j*HorSubTensorSize / 2d^RCHor [d][j][1] = (j==( NumHorSubTensorSplits – 1)) ? wd:(j+1)*HorSubTensorSize / 2d^RCHor [d][j][2] = RCHor [d][j][1] – RCHor [d][j][0]

[0114] cube_group_flag[comp] is 1-bit unsigned integer. cube_group_flag=0 indicates no cube_flag issignalled in one group, and all cube flags in the group are set to be 1. cube_group_flag=1 indicates cube flags of one group are signalled.

[0115] cube_flag[comp] is 1D array of size ((h4+7)^^3)^((w4+7)^^3) , which contains cube flags for primary component (comp =0). Value 1 indicates Skip Mode is applied to one cube of residual tensor ^^̂^^^. Value 0 indicates Skip Mode is disabled for one cube of residual tensor ^^̂^^^. If the comp value is 0, then the flag controls the primary component residual signalling, otherwise the secondary component residual signaling. Sizes h4, w4are defined in Table 2.

[0116] colour_transform_idx specifies the transformation between internal and output colour format,colour_transform_idx equal to 0 indicates no colour transformation, colour_transform_idx equal to 1 indicates the colour transformation with the same parameters as specified in sub-clause 8.8, colour_transform_idx equal to 2 indicates a colour transformation with user-defined parameters.

[0117] colour_transform_matrix[i][j] is a matrix of colour conversion, signalled only for colour_transform_idx equal to 2.

[0118] colour_transform_offset[i] is an offset for colour conversion, signalled only for colour_transform_idx equal to 2.

[0119] rvs_enable_flag[comp] is a flag used in the RVS for comp component. The flag 0 indicates RVSdisabled, 1 indicates RVS enabled.

[0120] grfs_enable_flag[comp] is an enable flag for channel-wise gain unit refinement scale tool, if grfs_enable_flag[comp] is equal to one then residual tensor elements in channel indicated by grfs_channel_flag[comp] for comp component are scaled.

[0121] grfs_channel_flag[comp] is an array with 1-bit flags. Its size depends on value of the comp. For comp equals to 0 the size is Cpand for comp equals to 1 the size is Cs. For channels with grfs_channel_flag[comp] equal to 0, the absolute value of comp component residual tensor is reduced, for channels with grfs_channel_flag[comp] equal to 1 the absolute value of comp component residual tensor isP24012302799WO1; G24N08582W (4824-54002) amplified. Here comp=0 indicates primary component and comp=1 indicates secondary component, number of channels for primary Cp and secondary Cs component latent tensor are defined in Table 2.

[0122] gain_3D_enable_flag is an enable flag for local quality control, if gain_3D_enable_flag is equal to 1, then residual tensor elements are scaled according to rules specified in sub-clause 14.2.

[0123] quality_map_entropy_index is an indicator which defines sigma index for quality map information decoding in me-tANS. Variable QMapEntropyIndex is set to quality_map_entropy_index.

[0124] multi_threading_z is a flag indicating multithreads is used for CodeStreamZ decoding

[0125] log2_num_threads_z_minus1 is an indicator for number of threads for CodeStreamZ decoding.

[0126] The variable NumberOfThreadsZ is set as follows:

[0127] If multi_threading_z = 0 then NumberOfThreadsZ = 1.

[0128] If multi_threading_z = 1 then NumberOfThreadsZ= 2<<(log2_num_threads_z_minus1 +1).

[0129] multi_threading_r[comp] is a flag indicating multithreads is used for CodeStreamR[comp] decoding.

[0130] log2_num_threads_r_minus1 [comp] is an indicator for number of threads for CodeStreamR[comp] decoding (comp=0..1).

[0131] For comp=0..1 – The variable NumberOfThreadsR[comp] are set as follows. – If multi_threading_r[comp] = 0, then NumberOfThreadsR[comp] = 1. – If multi_threading_r[comp] = 1, then NumberOfThreadsR[comp] = 2<<(log2_num_threads_r_minus1[comp] +1).

[0132] multi_threading_q is a flag indicating multithreads is used for CodeStreamQ decoding

[0133] log2_num_threads_q_minus1 is an indicator of the number of threads for CodeStreamQ decoding.

[0134] The variable NumberOfThreadsQ is set as follows:

[0135] If multi_threading_q = 0 then NumberOfThreadsQ = 1.

[0136] If multi_threading_q = 1 then NumberOfThreadsQ= 2<<(log2_num_threads_q_minus1 +1).

[0137] When present, additional_picture_header_bit[ i ] could have any value.

[0138] Let the variable NumPhBitsAtThisPoint be the total number of bits for all the syntax elements starting from the stream_profile_idc syntax element up to and excluding the additional_picture_header_bit

[0000] syntax element, when present, in the picture_header( ) syntax structure.

[0139] 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 instances of additional_picture_header_bit[ i ].

[0140] NOTE – instances of additional_picture_header_bit[ i ] can be extension bits only, byte alignmentbits only, or extension bits followed by byte alignment bits.P24012302799WO1; G24N08582W (4824-54002) ... 3. Technical problems solved by disclosed technical solutions

[0141] There lacks a design for signalling and storage of timed image sequences coded with JPEG AI in a media file. 4. A listing of solutions and embodiments

[0142] To solve the above-described problems, methods as summarized below are disclosed. The aspectsshould 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 media file format is specified, for storage of timed image sequences coded using the JPEG AI image codec specified in ISO / IEC 6048-1, and a video track carrying a timed image sequences coded using the JPEG AI image codec is referred to as a JPEG AI video track. a. In one example, the media file format is specified based on the ISO base media file format (ISOBMFF). b. In one example, the media file format is specified based on the high efficiency image file format (HEIF), which is in turn based on the ISO base media file format (ISOBMFF). 2) In one example, it is specified that each sample in a JPEG AI video track carries a JPEG AI coded image. 3) In one example, it is specified that for a conforming file containing at least one JPEG AI video track, the file type box shall either have a particular brand, e.g., ‘jai0’ or ‘jais’, as the major brand or include the particular brand within the compatibility brand list. a. In one example, it is specified that, when the particular brand is among the compatible brands, there shall be an image sequence track with the ‘jaim’ sample entry type, track_enabled equal to 1, track_in_movie equal to 1, and each sample entry having a data_reference_index value such that it is mapped to a DataEntryBox with (entry_flags & 1) equal to 1. b. In one example, it is specified that, readers for the particular brand shall be able to display an image sequence track with the ‘jaim’ sample entry type, track_enabled equal to 1 and track_in_movie equal to 1. 4) In one example, a particular sample entry type (also referred to as sample entry name), e.g., ‘jaim’, is specified for use by a motion JPEG AI video track. a. In one example, a sample entry of the particular sample entry type includes a configuration box that includes at least one or more of the following information: i. Information on the stream profile to which the JPEG AI coded images carried in the samples associated with the sample entry conforms. ii. Information on the decoder profiles provided by the JPEG AI coded images carried in the samples associated with the sample entry. iii. Information on the level to which the JPEG AI coded images carried in the samples associated with the sample entry conforms. iv. Information on the color format of the output pictures resulted from decoding the JPEG AI coded images carried in the samples associated with the sample entry.P24012302799WO1; G24N08582W (4824-54002) v. Information on the bit depth of the output pictures resulted from decoding the JPEG AI coded images carried in the samples associated with the sample entry. vi. Frame rate information of the sequence of the JPEG AI coded images carried in the samples associated with the sample entry. vii. Bit rate information of the sequence of the JPEG AI coded images carried in the samples associated with the sample entry. viii. Information on the color sampling modes, scaling factors, coded image color format, and output image color format of the sequence of the JPEG AI coded images carried in the samples associated with the sample entry. ix. Information on the partitioning of the sequence of the JPEG AI coded images carried in the samples associated with the sample entry into regions, e.g., a number of region rows and a number of region columns. 1. Information on whether each coded region is in its own substream. 2. Information on whether the partitioned regions are independent from each other. 5) In one example, it is specified that the suggested value for the Compressorname field is “\016Motion JPEG AI”, where \016 is 14, the length of the string as a byte. 6) In one example, a media subtype for the media type ‘image’ is specified, e.g., named ‘jais’, for JPEG AI coded image sequences carried in an ISOBMFF file or an HEIF file. a. In one example, it is specified that the presence of a sample entry of type ‘jaim’ is signalled by including a value whose first element is ‘jaim’ in the codecs parameter, which starts with ‘jaim’, followed by a dot (‘.’), further followed by a series of dot-separated (‘.’) values, where the dot-separated (‘.’) values include a subset of the information carried in the JPEG AI header item property specified by the above bullet item 4)a and its sub items, each value encoded as a hexadecimal number. 5. Embodiments

[0143] Below are some example embodiments for the aspects summarized above in Section 4, which can be applied to a potential standard specification of the JPEG AI image sequence file format and / or motion JPEG AI file format. 5.1 First Embodiment

[0144] This embodiment is for all items summarized above in Section 4. 1. Scope

[0145] This disclosure specifies container file formats for JPEG AI codestreams as specified in ISO / IEC 6048-1. It defines file formats for working with timed image sequence (also referred to as motion image sequence) files on computer platforms, allowing internet-based and other communications.

[0146] This disclosure uses already existing specifications for file formats and extends them for theembedding of JPEG AI codestreams.P24012302799WO1; G24N08582W (4824-54002) 2. Normative references

[0147] The following documents are referred to in the text in such a way that some or all of their content constitutes requirements of this disclosure. For dated references, only the edition cited applies. For undated references, the latest edition of the referenced document (including any amendments) applies. ISO / IEC 14496-12, Coding of audio-visual objects — Part 12: ISO base media file format ISO / IEC 23008-12:2017, Information technology — High efficiency coding and media delivery in heterogeneous environments — Part 12: Image File Format ISO / IEC 6048-1, Information technology — Learning-based image coding system (JPEG AI) — Part 1: Core coding system ISO / IEC 6048-2, Information technology — Learning-based image coding system (JPEG AI) — Part 2: Profiling Rec. ITU-T H.273 | ISO / IEC 23091-2, Coding-independent code points — Part 2: Video 3. Terms and definitions

[0148] For the purposes of this disclosure the terms and definitions given in ISO / IEC 14496-12, ISO / IEC 6048-1, ISO / IEC 6048-2, ISO / IEC 23008-12 and the following apply.

[0149] ISO and IEC maintain terminological databases for use in standardization at the following addresses: — ISO Online browsing platform: available at https: / / www.iso.org / obp — IEC Electropedia: available at http: / / www.electropedia.org / 3.1 box structured collection of data describing the image or the image decoding process 3.2 box type kind of information stored with the box (3.1) 3.3 byte group of 8 bits 3.4 coding-independent code point code point based on enumerated values for the definition of the colourspaces Note 1 to entry: Code points defined in Rec. ITU-T H.273 | ISO / IEC 23091-2. 3.5 high efficiency image file format image file format which can embed still images and motion sequences (3.7) Note 1 to entry: Based on ISO / IEC 23008-12. 3.6 image collectionP24012302799WO1; G24N08582W (4824-54002) unordered set of images without an implied or signalled presentation order or presentation time stamps 3.7 motion sequence movie timed sequence (3.9) of images 3.8 sample <ISOBMFF> all the data associated with a single time Note 1 to entry: This definition is used in Annexes B and C as data associated with one coded image in a sequence. 3.9 timed sequence linearly ordered sequence of media entities such as images where each entity is presented at a well defined time stamp 4. Symbols and abbreviated terms 4.1 Symbols Picture() JPEG AI codestream as defined in ISO / IEC 6048-1 5. Abbreviated terms

[0150] For the purposes of this disclosure the abbreviated terms given in ISO / IEC 14496-12, ISO / IEC 6048-1, ISO / IEC 6048-2, ISO / IEC 23008-12 and the following apply. CICP coding-independent code points HEIF high efficiency image file format ISOBMFF iso base media file format 6. Naming conventions for numerical values

[0151] Integer numbers are expressed as bit patterns, hexadecimal values, or decimal numbers. Bit patterns and hexadecimal values have both a numerical value and an associated particular length in bits.

[0152] Hexadecimal notation, indicated by prefixing the hexadecimal number by “0x”, may be used instead of binary notation to denote a bit pattern having a length that is an integer multiple of 4. For example, 0x41 represents an eight-bit pattern having only its second most significant bit and its least significant bit equal to 1. Numerical values that are specified under a “Code” heading in tables that are referred to as “code tables” are bit pattern values (specified as a string of digits equal to 0 or 1 in which the left-most bit is considered the most-significant bit). Other numerical values not prefixed by “0x” are decimal values. When used in expressions, a hexadecimal value is interpreted as having a value equal to the value of the corresponding bit pattern evaluated as a binary representation of an unsigned integer (i.e., as the value of the number formed by prefixing the bit pattern with a sign bit equal to 0 and interpreting the result as a two’s complement representation of an integer value). For example, the hexadecimal value 0xF is equivalent to the 4-bit pattern ‘1111’ and is interpreted in expressions as being equal to the decimal number 15.P24012302799WO1; G24N08582W (4824-54002) 7. Conformance

[0153] This disclosure shares common definitions for the structure of files (a sequence of objects, called boxes here, and atoms in other similar file formats), and a common definition of the general structure of an object (the size and type).

[0154] File formats representing either images, or image sequences shall be as specified in Annexes A and B. All these specifications require that readers ignore objects that are unrecognizable to them.

[0155] This disclosure takes precedence over those on which it is based, in any case where there are differences or conflicts; however, no such conflicts are known to exist.

[0156] For better readability and understanding, the syntax description for the different file formats isdone in the same way as in the base formats. 8. Colour specification

[0157] JPEG AI (as defined in ISO / IEC 6048-1) describes only the encoded bitstream of an image. In order to properly display or interpret the image, it is essential that the colourspace of that image data is properly characterized. For this purpose, the respective container file format has to signal the correct colourspace. The defined formats in this disclosure for JPEG AI signals the colour space as specified in Rec. ITU-T H.273 | ISO / IEC 23091-2. 9. Organization of the disclosure

[0158] Annex A specifies the integration of JPEG AI codestreams in the ISOBMFF (as defined in ISO / IEC 14496-12) for use of image sequences as movie in a file format.

[0159] Annex B specifies the integration of JPEG AI codestreams in the HEIF file format (as defined in ISO / IEC 23008-12) allowing the integration of JPEG AI coded image sequences. Annex A (normative) Use of JPEG AI codestreams in the ISOBMFF - Motion JPEG AI A.1 General

[0160] This annex specifies the use of JPEG AI coding for timed sequences of images within files based on the ISO base media file format (defined in ISO / IEC 14496-12), denoted Motion JPEG AI. The Motion JPEG AI file format is designed to contain one or more motion sequences of JPEG AI compressed images, with their timing. It is intended as a ‘building block’, specifying only the video format. An application would be expected to combine Motion JPEG AI with suitable audio, metadata, etc. for a complete application specification; that specification would normally select profiles and levels of Motion JPEG AI, and can also specify application profiles and levels that apply to the integration.

[0161] Motion JPEG AI is expected to be used in a variety of applications, particularly where JPEG AI coding technology is already available for other reasons, or where the high-quality frame-based approach, with no inter-frame coding, is appropriate. These application areas include: — digital still cameras, — error-prone environments such as wireless and the internet, — video capture,P24012302799WO1; G24N08582W (4824-54002) — high quality digital video recording for professional broadcasting and motion picture production from film-based to digital systems, — and high-resolution medical and satellite imaging.

[0162] Motion JPEG AI is a flexible format, permitting a wide variety of usages, such as editing, display,interchange, and streaming.

[0163] NOTE A sample in the context of ISOBMFF (ISO / IEC 14496-12) is “all the data associated with a single time”. In this annex, it is meant as data associated with one coded image, not a “pixel”. A.2 Compatibility and technology derivation A.2.1 Family members

[0164] This is a ‘building block’ specification; it defines how to store motion JPEG AI sequences in a file format based on the ISO base media file format. It stands as a member of a family of specifications with common formatting.

[0165] Since this is a building block specification, if audio is needed, then suitable audio support should be selected from other specifications using the ISO base media file format (ISO / IEC 14496-12).

[0166] These specifications share a common definition for the structure of a file (a sequence of objects, called boxes here, and atoms in other similar file formats), and a common definition of the general structure of an object (the size and type).

[0167] All these specifications require that readers ignore objects that are unrecognizable to them.

[0168] This specification takes precedence over those on which it is based, in any case where there are differences or conflicts; however, no such conflicts are known to exist. A.2.2. Conformance

[0169] Implementations of motion JPEG AI decoders shall support the decoding of video tracks usingthe JPEG AI coding technology. Files conforming to this version of this specification shall contain at least one motion JPEG AI video track and the file type box shall either have ‘jai0’ as the major brand or include ‘jai0’ as a brand within the compatibility list. Derived and application specifications based on this specification may define additional brands. A.3 Sample entry and sample formats for motion sequences A.3.1 General

[0170] The sample entry and sample formats for JPEG AI codestreams in the ISOBMFF are derived from the syntax in ISO / IEC 14496-12 and defined in A.3.2 to A.3.5. A.3.2 Definition Sample Entry Type: ‘jaim’ Container: Sample Description Box (‘stsd’) Mandatory: Yes Quantity: One or more sample entries may be present Box Type: ‘jaiC’P24012302799WO1; G24N08582W (4824-54002) Container: Motion JPEG AI Sample Entry (‘jaim’) Mandatory: Yes Quantity: One

[0171] The format of a sample (3.8) when the sample entry name is ‘jaim’ is a JPEG AI codestream, called Picture (), as defined in ISO / IEC 6048-1.

[0172] Each image presented to a JPEG AI decoder is the content of a sample.

[0173] The values present in the VisualSampleEntry, its constituent boxes, and the codestreams that theseboxes describe, shall agree, to the extent that the format and precision of the fields allow. This agreement includes, but is not limited to, width and height information, and the resolution declaration (within the accuracy permitted by the different representations). Files with conflicts are non-conforming and readers may attempt to decide which values are correct, or reject the file.

[0174] The fields width and height in the Visual Sample Entry indicate the highest resolution component of the image (which is typically, but not required to be, the luminance, in an image in which not all components have the same spatial sampling density).

[0175] If the coded images contain an alpha plane, a suitable value of ‘depth’, as indicated in the Visual Sample Entry, shall be used.

[0176] Colour information may be supplied in one or more ColourInformationBoxes. These should be placed in order in the sample entry starting with the most accurate (and potentially the most expensive to process), in progression to the least. These are advisory and concern rendering and colour conversion, and there is no normative behaviour associated with them; a reader may choose to use the most suitable. A ColourInformationBox with an unknown colour type may be ignored. Values of the field colour_type other than those documented here are reserved.

[0177] The ColourInformationBox is specific to the VideoSampleEntry defined in ISO / IEC 14496-12. A.3.3 Syntax / / Visual Sequences class JAIMSampleEntry() extends VisualSampleEntry (‘jaim’){ JAIMConfigurationBox(); ColourInformationBox(); / / as defined in ISO / IEC 14496-12 } class JAIMConfigurationBox extends Box(‘jaiC’) { unsigned int(8) configurationVersion = 1; unsigned int(8) stream_profile_idc; unsigned int(8) num_decoder_profiles_minus1; for (i=0; i <= num_decoder_profiles_minus1; i++) unsigned int(8) decoder_profile_idc[i]; unsigned int(8) level_idc bit(2) reserved = ‘11’b;P24012302799WO1; G24N08582W (4824-54002) unsigned int(2) colour_format_idc; unsigned int(3) bit_depth_idc; unsigned int(1) constantFrameRate; unsigned int(16) avgFrameRate; BitRateBox(); / / optional }

[0178] Alternatively, the syntax of JAIMConfigurationBox is as follows:class JAIMConfigurationBox extends Box(‘jaiC’) { unsigned int(8) configurationVersion = 1; unsigned int(4) stream_profile_idc; unsigned int(4) num_decoder_profiles_minus1; for (i=0; i <= num_decoder_profiles_minus1; i++) unsigned int(4) decoder_profile_idc[i]; unsigned int(4) level_idc if(num_decoder_profiles_minus1 % 2 == 1) unsigned int(4) byte_alignment_4bits = ‘1111’b; unsigned int(3) bit_depth_idc; unsigned int(1) s_ver_minus1; unsigned int(1) s_hor_minus1; unsigned int(1) c_ver_minus1; unsigned int(1) c_hor_minus1; bit(1) reserved = ‘1’b; unsigned int(1) regions_independent_flag; unsigned int(7) num_region_rows_minus1; unsigned int(7) num_region_cols_minus1; unsigned int(1) constantFrameRate; unsigned int(16) avgFrameRate; BitRateBox(); / / optional } A.3.4 Semantics

[0179] In the JAIMConfigurationBox(): — stream_profile_idc, num_decoder_profiles_minus1, decoder_profile_idc[i], level_idc, colour_format_idc, and bit_depth_idc contain the matching values for the fields stream_profile_idc, num_decoder_profiles_minus1, decoder_profile_idc[ i ], level_idc, picture_format, and bit_depth_idc as defined in ISO / IEC 6048-1, for each of the JPEG AI codestreams carried in the samples to which the sample entry containing this configuration box applies (simply referred to as “the stream” below).

[0180] Alternatively, the semantics are as follows:P24012302799WO1; G24N08582W (4824-54002) — stream_profile_idc, num_decoder_profiles_minus1, decoder_profile_idc[i], level_idc, bit_depth_idc, s_ver_minus1, s_hor_minus1, c_ver_minus1, c_hor_minus1, regions_independent_flag, num_region _rows_minus1, and num_region_cols_minus1 contain the matching values for the fields stream_profile_idc, num_decoder_profiles_minus1, decoder_profile_idc[ i ], level_idc, bit_depth_idc, s_ver_minus1, s_hor_minus1, c_ver_minus1, c_hor_minus1, region_residual_in_its_own_ substream_flag, num_ver_splits_minus1, and num_hor_splits_minus1 as defined in ISO / IEC 6048-1, for each of the JPEG AI codestreams carried in the samples to which the sample entry containing this configuration box applies (simply referred to as “the stream” below). — constantFrameRate equal to 1 indicates that the stream is of constant frame rate. Value 0 indicates that the stream may or may not be of constant frame rate. — avgFrameRate gives the average frame rate, in units of frames / (256 seconds), for the stream. Value 0 indicates an unspecified average frame rate.

[0181] In the Visual Sample Entry: — Compressorname the value “\016Motion JPEG AI” is suggested but not required (\016 is 14, the length of the string as a byte) — depth takes one of the following values; other values are reserved, and if found, the composition behaviour is undefined 0x18 – images are in colour with no alpha 0x28 – images are in colour with alpha Annex B (normative) Use of JPEG AI coded image sequences in the HEIF image file format B.1 General

[0182] This annex specifies a format to encapsulate JPEG AI coded image sequences in the HEIF image file format specified in ISO / IEC 23008-12. Brands for image sequence are specified in B.3.

[0183] NOTE A sample in the context of ISOBMFF (ISO / IEC 14496-12) is “all the data associated with a single time”. In this annex, it is meant as data associated with one coded image, not a “pixel”. B.2 JPEG AI image sequences B.2.1. General

[0184] Clause B.2 specifies requirements for all files containing one or more JPEG AI coded image sequence tracks. When a brand specified in subclause B.3.2 is among the compatible brands of a file, the requirements specified in B.2 shall be obeyed.

[0185] The specifications of ISO / IEC 23008-12:2017, Clause 7 apply. B.2.2 Derivation from ISO / IEC 14496-12

[0186] The sample entry of type ‘jaim’ shall be used for an image sequence track coded with JPEG AI, as defined in A.3, using the JAIMSampleEntry() and sample format as specified in A.3.

[0187] For a track containing a JPEG AI image sequence, all samples (3.8) are sync samples.P24012302799WO1; G24N08582W (4824-54002) B.3 JPEG AI-specific brands B.3.1 JPEG AI image sequence brands B.3.1.1 General

[0188] The brand ‘jais’ is specified in the following subclauses.B.3.1.2 Requirements on HEIF files

[0189] Files shall include ‘msf1’ among the compatible brands and hence conform to the specifications in ISO / IEC 23008-12:2017, A.3.1.1. Additionally, files shall conform to the specifications in B.2. The value of track_enabled shall be equal to 1 and the value of track_in_movie shall be equal to 1 for at least one image sequence track conforming to the specifications in B.2.

[0190] When the ‘jais’ brand is among the compatible brands, there shall be an image sequence track with the ‘jaim’ sample entry type, track_enabled equal to 1, track_in_movie equal to 1, and each sample entry having a data_reference_index value such that it is mapped to a DataEntryBox with (entry_flags & 1) equal to 1. B.3.1.3 Requirements on HEIF readers

[0191] The requirements on readers specified in ISO / IEC 23008-12:2017, A.3.1.2 shall be supported.

[0192] Readers for the ‘jais’ brand shall be able to display an image sequence track with the ‘jaim’ sampleentry type, track_enabled equal to 1 and track_in_movie equal to 1.

[0193] Readers shall support all values allowed by ISO / IEC 23008-12:2017, 7.2.1 for the matrix syntax element of the TrackHeaderBox and shall obey the CleanApertureBox of the visual sample entry when displaying an image sequence track with the ‘jaim’ sample entry.

[0194] In other words, readers are required to support rotation by 0, 90, 180, and 270 degrees, as controlled by the matrix syntax element, as well as cropping, as controlled by the CleanApertureBox.

[0195] Displaying of an image sequence track with opacity information specified as part of the JPEG AI codestream or by an associated auxiliary track of aux_track_type equal to urn:mpeg:hevc:2015:auxid:1 should be supported. B.4 JPEG AI coded image sequence in ISO / IEC 23008-12 image files media type registration B.4.1 General

[0196] The file extension and media type of a file deriving from the ISO base media file format usually reflect the major brand in the FileTypeBox. When the major brand indicates a brand related to subclause B.4.2 (image sequence), the media type defined here should be used. When such a brand is a compatible brand, this media type may also be used. Subclause B.4.2 provides a media type registration, following Internet Engineering Task Force (IETF) Request for Comments (RFC) 6838. B.4.2 Registration

[0197] Media type name: image

[0198] Media subtype name: jais

[0199] Required parameters: noneP24012302799WO1; G24N08582W (4824-54002)

[0200] Optional parameters: Same as for the media type image / heif. The presence of a sample entry of type ‘jaim’ is signalled by including a value whose first element is ‘jaim’ in the codecs parameter, for which the value starts with ‘jaim’ followed by a dot (‘.’), further followed by a series of dot-separated (‘.’) values from the JAIMConfigurationBox() as specified in clause A.3 of ISO / IEC 6048-5, starting from stream_profile_idc up to and includingeach encoded as a hexadecimal number.

[0201] Encoding considerations: binary Note: None

[0202] Security considerations: See Media type image / heif. In addition, sample entries of type ‘jaim’ contain structures of variable length and have an extensible syntax. Both aspects present potential security risks for implementations. In particular, variable length structures present buffer overflow risks and extensible syntax could result in the triggering of adverse actions.

[0203] Interoperability considerations: Same as for the Media type image / heif. In addition, sample entries of type ‘jaim’ can conform to one of several profiles and / or require one of several capabilities, e.g. as specified in ISO / IEC 6048-2 – not all of which are necessarily supported by a receiving decoder. As a result, decoders might attempt to process the contents only to determine that they cannot be rendered either partially or in full.

[0204] Published specification: ISO / IEC 6048-5, Information technologies — Learning-based Image Coding — Part 5: JPEG AI file formats

[0205] Applications: Multimedia, Imaging, Pictures, Scientific

[0206] Fragment identifier considerations: same as for Media type image / heif

[0207] Restrictions on usage: None

[0208] Additional information: Depreciated alias names: N / A Magic number(s): None File extension(s): jais Macintosh File Type Code(s): N / A Object Identifiers: N / A

[0209] Intended usage: CommonNotes: None 7. References [1] IETF RFC 6838, Media Type Specifications and Registration Procedures [2] ISO / IEC 14496-12: “Information technology — Coding of audio-visual objects — Part 12: ISO base media file format”. [3] ISO / IEC 23009-1: “Information technology — Dynamic adaptive streaming over HTTP (DASH) — Part 1: Media presentation description and segment formats”.P24012302799WO1; G24N08582W (4824-54002) [4] ISO / IEC 14496-15: “Information technology — Coding of audio-visual objects — Part 15: Carriage of network abstraction layer (NAL) unit structured video in the ISO base media file format”. [5] ISO / IEC 23008-12: “Information technology — High efficiency coding and media delivery in heterogeneous environments — Part 12: Image File Format”.

[0210] FIG. 2 is a block diagram showing an example video processing system 4000 in which varioustechniques 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 may 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.

[0211] 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 techniques 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.

[0212] 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.

[0213] FIG. 3 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 (IoT) 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 hardwareP24012302799WO1; G24N08582W (4824-54002) circuitry, some techniques 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.

[0214] FIG. 4 is a flowchart for an example method 4200 of video processing. The method 4200 determines to specify a particular sample entry type for use by a motion Joint Photographic Experts Group Artificial Intelligence (JPEG AI) code stream (a.k.a., video track, image codec, or bitstream) at step 4202. A conversion between a visual media data and a bitstream is performed based on the particular sample entry type specified as the motion JPEG AI code stream at step 4204. The conversion may include encoding at an encoder, decoding at a decoder, or combinations thereof.

[0215] 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.

[0216] FIG. 5 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 may 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.

[0217] 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 medium / server 4340 for access by destination device 4320.

[0218] 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 may 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 configured to interface with an external display device.P24012302799WO1; G24N08582W (4824-54002)

[0219] 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 (VVC) standard and other current and / or further standards.

[0220] FIG. 6 is a block diagram illustrating an example of video encoder 4400, which may be video encoder 4314 in the system 4300 illustrated in FIG.5. Video encoder 4400 may be configured to perform any or all of the techniques of this disclosure. The video encoder 4400 includes a plurality of functional components. The techniques described in this disclosure may be shared among the various components of video encoder 4400. In some examples, a processor may be configured to perform any or all of the techniques described in this disclosure.

[0221] 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.

[0222] 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 picture is a picture where the current video block is located.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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.P24012302799WO1; G24N08582W (4824-54002)

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] As discussed above, video encoder 4400 may predictively signal the motion vector. Two examples of predictive signaling techniques that may be implemented by video encoder 4400 include advanced motion vector prediction (AMVP) and merge mode signaling.

[0234] 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 mayP24012302799WO1; G24N08582W (4824-54002) 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.

[0235] Residual generation unit 4407 may generate residual data for the current video block bysubtracting 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.

[0236] 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.

[0237] Transform 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.

[0238] 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.

[0239] Inverse quantization unit 4410 and inverse transform unit 4411 may apply inverse quantization and inverse transforms to the transform 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.

[0240] After reconstruction unit 4412 reconstructs the video block, the loop filtering operation may beperformed to reduce video blocking artifacts in the video block.

[0241] Entropy encoding unit 4414 may 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.

[0242] FIG. 7 is a block diagram illustrating an example of video decoder 4500 which may be video decoder 4324 in the system 4300 illustrated in FIG.5. 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.

[0243] In the example shown, video decoder 4500 includes an entropy decoding unit 4501, a motioncompensation 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 someP24012302799WO1; G24N08582W (4824-54002) examples, perform a decoding pass generally reciprocal to the encoding pass described with respect to video encoder 4400.

[0244] 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.

[0245] 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.

[0246] Motion compensation unit 4502 may use interpolation filters as used by video encoder 4400 during 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.

[0247] Motion compensation unit 4502 may use some of the syntax information to determine sizes ofblocks 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.

[0248] 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., de-quantizes, the quantized video block coefficients provided in the bitstream and decoded by entropy decoding unit 4501. Inverse transform unit 4505 applies an inverse transform.

[0249] Reconstruction unit 4506 may sum the residual blocks with the corresponding prediction blocksgenerated 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.

[0250] FIG. 8 is a schematic diagram of an example encoder 4600. The encoder 4600 is suitable for implementing the techniques of VVC. The encoder 4600 includes three in-loop filters, namely a deblocking filter (DF) 4602, a sample adaptive offset (SAO) 4604, and an adaptive loop filter (ALF) 4606. Unlike the DF 4602, which uses predefined filters, the SAO 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.P24012302799WO1; G24N08582W (4824-54002)

[0251] 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 SAO 4604, and the ALF 4606 for filtering prior to those images being stored in the reference picture buffer 4612.

[0252] A listing of solutions preferred by some examples is provided next.

[0253] The following solutions show examples of techniques discussed herein.

[0254] 1. A method for processing media data comprising: determining a media file format is specified for storage of timed image sequences coded using a Joint Photographic Experts Group Artificial Intelligence (JPEG AI) image codec, and a video track carrying a timed image sequence coded using the JPEG AI image codec is referred to as a JPEG AI video track.; and performing a conversion between a visual media data and a bitstream based on the JPEG AI image codec.

[0255] 2. The method of solution 1, wherein the media file format is specified based on the ISO base media file format (ISOBMFF).

[0256] 3. The method of solution 1, wherein the media file format is specified based on the high efficiency image file format (HEIF), which is in turn based on the ISO base media file format (ISOBMFF).

[0257] 4. The method of any of solutions 1-3, wherein each sample in a JPEG AI video track carries a JPEG AI coded image.

[0258] 5. The method of any of solutions 1-4, wherein for a conforming file containing at least one JPEG AI video track, the file type box shall either have a particular brand as the major brand or include the particular brand within the compatibility brand list.

[0259] 6. The method of any of solutions 1-5, wherein the particular brand is ‘jai0’ or ‘jais’.

[0260] 7. The method of any of solutions 1-6, wherein when the particular brand is among the compatible brands, there shall be an image sequence track with the ‘jaim’ sample entry type, track_enabled equal to 1, track_in_movie equal to 1, and each sample entry having a data_reference_index value such that it is mapped to a DataEntryBox with (entry_flags & 1) equal to 1.

[0261] 8. The method of any of solutions 1-7, wherein readers for the particular brand shall be able to display an image sequence track with the ‘jaim’ sample entry type, track_enabled equal to 1 and track_in_movie equal to 1.P24012302799WO1; G24N08582W (4824-54002)

[0262] 9. The method of any of solutions 1-8, wherein a particular sample entry type, also referred to as sample entry name, is specified for use by a motion JPEG AI video track.

[0263] 10. The method of any of solutions 1-9, wherein the particular sample entry type is ‘jaim’.

[0264] 11. The method of any of solutions 1-10, wherein a sample entry of the particular sample entry type includes a configuration box that includes one or more of the following information: information on the stream profile to which the JPEG AI coded images carried in the samples associated with the sample entry conforms; information on the decoder profiles provided by the JPEG AI coded images carried in the samples associated with the sample entry; information on the level to which the JPEG AI coded images carried in the samples associated with the sample entry conforms; information on the color format of the output pictures resulted from decoding the JPEG AI coded images carried in the samples associated with the sample entry; information on the bit depth of the output pictures resulted from decoding the JPEG AI coded images carried in the samples associated with the sample entry; frame rate information of the on the sequence of the JPEG AI coded images carried in the samples associated with the sample entry; and bit rate information of the on the sequence of the JPEG AI coded images carried in the samples associated with the sample entry

[0265] 12. The method of any of solutions 1-11, wherein the suggested value for the Compressorname field is “\016Motion JPEG AI”, where \016 is 14, the length of the string as a byte.

[0266] 13. The method of any of solutions 1-12, wherein a media subtype for the media type ‘image’ is specified for JPEG AI coded image sequences carried in an ISOBMFF file or an HEIF file.

[0267] 14. The method of any of solutions 1-13, wherein the media subtype is ‘jais’.

[0268] 15. The method of any of solutions 1-14, wherein the presence of a sample entry of type ‘jaim’ is signalled by including a value whose first element is ‘jaim’ in the codecs parameter, which starts with ‘jaim’, followed by a dot (‘.’), further followed by a series of dot-separated (‘.’) values, where the dot-separated (‘.’) values include a subset of the information carried in the JPEG AI header item property, each value encoded as a hexadecimal number.

[0269] 16. The method of any of solutions 1-15, wherein the conversion includes encoding the visual media data into the bitstream.

[0270] 17. The method of any of solutions 1-15, wherein the conversion includes decoding the visual media data from the bitstream.

[0271] 18. 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 1-17.

[0272] 19. 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 storedP24012302799WO1; G24N08582W (4824-54002) 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 1-17.

[0273] 20. 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 a media file format is specified for storage of timed image sequences coded using a Joint Photographic Experts Group Artificial Intelligence (JPEG AI) image codec, and a video track carrying a timed image sequence coded using the JPEG AI image codec is referred to as a JPEG AI video track; and generating a bitstream based on the determining.

[0274] 21. A method for storing bitstream of a video comprising: determining a media file format is specified for storage of timed image sequences coded using a Joint Photographic Experts Group Artificial Intelligence (JPEG AI) image codec, and a video track carrying a timed image sequence coded using the JPEG AI image codec is referred to as a JPEG AI video track; generating a bitstream based on the determining; and storing the bitstream in a non-transitory computer-readable recording medium.

[0275] 22. A method, apparatus, or system described in the present disclosure.

[0276] 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.

[0277] 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, during 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.

[0278] 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 machinesP24012302799WO1; G24N08582W (4824-54002) 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.

[0279] 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 file in a file system. A program can be stored in a portion of a file 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.

[0280] 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).

[0281] Processors suitable for the execution of a computer program include, by way of example, bothgeneral 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 memory 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.

[0282] 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 singleP24012302799WO1; G24N08582W (4824-54002) 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.

[0283] 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.

[0284] 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.

[0285] 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.

[0286] While several embodiments have been provided in the present disclosure, it should be understood that the disclosed systems and methods might be embodied in many 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.

[0287] 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

P24012302799WO1; G24N08582W (4824-54002) CLAIMS What is claimed is:

1. A method for processing media data, comprising: determining to specify a particular sample entry type for use by a motion Joint Photographic Experts Group Artificial Intelligence (JPEG AI) code stream; and performing a conversion between a visual media data and a bitstream based on the particular sample entry type specified as the motion JPEG AI code stream.

2. The method of claim 1, wherein the particular sample entry type is referred to as a sample entry name.

3. The method of claim 1, wherein the particular sample entry type is referred to as a ‘jaim’.

4. The method of any of claims 1-3, wherein a sample entry of the particular sample entry type includes a configuration box.

5. The method of claim 4, wherein the configuration box contains information corresponding to a stream profile to which JPEG AI coded images carried in samples associated with the sample entry conform.

6. The method of any of claims 4-5, wherein the configuration box contains information corresponding to decoder profiles provided by JPEG AI coded images carried in samples associated with the sample entry.

7. The method of any of claims 4-6, wherein the configuration box contains information corresponding to a level to which JPEG AI coded images carried in samples associated with the sample entry conform.

8. The method of any of claims 4-7, wherein the configuration box contains information corresponding to a color format of output pictures resulting from decoding JPEG AI coded images carried in samples associated with the sample entry.

9. The method of any of claims 4-8, wherein the configuration box contains information corresponding to a bit depth of output pictures resulting from decoding JPEG AI coded images carried in samples associated with the sample entry.

10. The method of any of claims 4-9, wherein the configuration box contains information corresponding to a frame rate of a sequence of JPEG AI coded images carried in samples associated with the sample entry.

11. The method of any of claims 4-10, wherein the configuration box contains information corresponding to a bit rate of a sequence of JPEG AI coded images carried in samples associated with the sample entry.P24012302799WO1; G24N08582W (4824-54002) 12. The method of any of claims 4-11, wherein the configuration box contains information corresponding to one or more of color sampling modes, scaling factors, a coded image color format, and a output image color format.

13. The method of any of claims 4-12, wherein the configuration box contains information corresponding to partitioning of a picture into regions.

14. The method of claim 13, wherein the regions comprise one or more of a number of region rows and a number of region columns.

15. The method of any of claims 4-14, wherein the configuration box contains information indicating whether each coded region is in its own substream.

16. The method of any of claims 4-14, wherein the configuration box contains information indicating whether partitioned regions are independent from each other.

17. The method of any of claims 1-16, wherein the conversion includes encoding the visual media data into the bitstream.

18. The method of any of claims 1-16, wherein the conversion includes decoding the visual media data from the bitstream.

19. 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 claims 1-18.

20. 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 1-18.

21. 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 to specify a particular sample entry type for use by a motion Joint Photographic Experts Group Artificial Intelligence (JPEG AI) code stream; and generating a bitstream based on the particular sample entry type specified as the motion JPEG AI code stream.P24012302799WO1; G24N08582W (4824-54002) 22. A method for storing bitstream of a video comprising: determining to specify a particular sample entry type for use by a motion Joint Photographic Experts Group Artificial Intelligence (JPEG AI) code stream; generating a bitstream based on the determining; and storing the bitstream in a non-transitory computer-readable recording medium.

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

Images