Signaling of rendering information in neural network based image bitstreams

Abstract

A mechanism of processing video data is disclosed. The mechanism comprises: determining to signal dynamic metadata rendering information in a joint photographic experts group (JPEG) artificial intelligence (AI) bitstream, wherein the dynamic metadata rendering information is signaled in a syntax structure comprising: an indication of a dynamic metadata type, an indication of a size of the dynamic metadata, and data bytes of the dynamic metadata; performing a conversion between visual media data and the JPEG AI bitstream based on the dynamic metadata rendering information.

Description

[0001] Cross-references to related applications

[0002] This application claims priority and benefit to U.S. Provisional Patent Application No. 63 / 558,508, filed February 27, 2024, and U.S. Provisional Patent Application No. 63 / 564,599, filed March 13, 2024. All of the foregoing patent applications are incorporated herein by reference in their entirety. Technical Field

[0003] This patent document relates to the generation, storage, and use of digital audio and video media information in file formats. Background Technology

[0004] Digital video accounts for the largest share of 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 is likely to continue to grow. Summary of the Invention

[0005] The first aspect relates to a method for processing video data, comprising: determining dynamic metadata rendering information transmitted via signaling in a Joint Group of Image Experts (JPEG) Artificial Intelligence (AI) bitstream, wherein the dynamic metadata rendering information is transmitted via signaling in a syntactic structure comprising: an indication of the type of dynamic metadata, an indication of the size of the dynamic metadata, and data bytes of the dynamic metadata; and performing a conversion between visual media data and the JPEG AI bitstream based on the dynamic metadata rendering information.

[0006] The second aspect relates to an apparatus for processing video data, including a processor and a non-transitory memory having instructions thereon, wherein the instructions, when executed by the processor, cause the processor to perform any of the aforementioned aspects.

[0007] The third aspect relates to a non-transitory computer-readable medium, including a computer program product for use by a video codec device, the computer program product including computer-executable instructions stored on the non-transitory computer-readable medium, such that when the computer-executable instructions are executed by a processor, the video codec device performs the methods of any of the preceding aspects.

[0008] The fourth aspect relates to a non-transitory computer-readable recording medium storing a JPEG AI stream of video generated by a method performed by a video processing apparatus, wherein the method includes: determining dynamic metadata rendering information in the Joint Picture Experts Group (JPEG) Artificial Intelligence (AI) stream by signaling, wherein the dynamic metadata rendering information is transmitted by signaling in a syntactic structure including: an indication of the type of dynamic metadata, an indication of the size of the dynamic metadata, and data bytes of the dynamic metadata; and generating a JPEG AI stream based on the determination.

[0009] The fifth aspect relates to a method for storing a bitstream of video, comprising: determining dynamic metadata rendering information in a Joint Picture Experts Group (JPEG) Artificial Intelligence (AI) bitstream by signaling, wherein the dynamic metadata rendering information is signaled in a syntactic structure including: an indication of the type of dynamic metadata, an indication of the size of the dynamic metadata, and data bytes of the dynamic metadata; generating a JPEG AI bitstream based on the determination; and storing the JPEG AI bitstream in a non-transitory computer-readable recording medium.

[0010] For clarity, any of the embodiments described above may be combined with one or more other embodiments described above to create new embodiments within the scope of this disclosure.

[0011] These and other features will become clearer through the following detailed description of the embodiments with reference to the accompanying drawings and claims. Attached Figure Description

[0012] To gain a more complete understanding of this disclosure, reference is now made to the following brief description, taken in conjunction with the accompanying drawings and detailed description, wherein like reference numerals denote like parts.

[0013] Figure 1 This is a block diagram illustrating an example video processing system.

[0014] Figure 2 This is a block diagram of an example video processing device.

[0015] Figure 3 This is a flowchart of an example method for video processing.

[0016] Figure 4 This is a block diagram illustrating an example video codec system.

[0017] Figure 5 This is a block diagram showing an example encoder.

[0018] Figure 6 This is a block diagram showing an example decoder.

[0019] Figure 7This is a schematic diagram of an example encoder.

[0020] Figure 8 This is a flowchart of an example method for video processing. Detailed Implementation

[0021] First, it should be understood that although illustrative implementations of one or more embodiments are provided below, the disclosed systems and / or methods can be implemented using any number of techniques, whether currently known or yet to be developed. This disclosure should not be limited in any way to the illustrative implementations, drawings, and techniques described below, including the example designs and implementations shown and described herein, but modifications can be made within the scope of the appended claims and their equivalents.

[0022] 1. Preliminary Discussion

[0023] This document relates to image and video encoding and decoding based on neural networks (NNs). Specifically, this disclosure relates to signaling of information rendered in image or video bitstreams (such as Joint Image Experts Group (JPEG) Artificial Intelligence (AI) bitstreams, which may also be referred to as bitstreams) based on neural networks (NNs). This idea can be applied alone or in various combinations to image and / or video encoding and decoding methods and specifications.

[0024] 2. Further discussion

[0025] Deep learning has made rapid progress in various fields, especially in computer vision and image processing. Inspired by the tremendous success of deep learning in computer vision, many researchers have shifted their attention from image / video compression techniques to neural image / video compression. Neural networks are designed through interdisciplinary research in neuroscience and mathematics. They have demonstrated powerful capabilities in nonlinear transformations and classification. Significant progress has been made in neural network-based image / video compression techniques. Examples of neural network-based image compression algorithms have reportedly achieved rate-distortion (RD) performance comparable to Multifunctional Video Coding (VVC), a video coding standard developed by the Joint Video Experts Group (JVET), comprised of experts from the Moving Picture Experts Group (MPEG) and the Video Codec Experts Group (VCEG). With the continuous improvement of neural image compression performance, neural network-based video compression has become an actively developing research area. However, due to the inherent difficulties of the problem, neural network-based video coding is still in its early stages.

[0026] 2.1 Image / Video Compression

[0027] Image / video compression (also known as image / video encoding / decoding) generally refers to the computational technique of compressing images or videos into binary code for convenient storage and transmission. Binary code may or may not support lossless reconstruction of the original image or video; this is called lossless compression and lossy compression. Since lossless reconstruction is not necessary in most cases, most efforts focus on lossy compression. The performance of image or video compression algorithms is typically evaluated from two aspects: compression ratio and reconstruction quality. The compression ratio is directly related to the amount of binary code; less is better. Reconstruction quality is measured by comparing the reconstructed image or video with the original image or video; higher is better.

[0028] Image / video compression techniques can be divided into two branches: classical video encoding / decoding methods and neural network-based video compression methods. Classical video encoding / decoding schemes employ transform-based solutions, where researchers model dependencies in the quantization domain through carefully hand-designed entropy encoding / decoding, thereby leveraging statistical dependencies in latent variables (e.g., Discrete Cosine Transform (DCT) or wavelet coefficients). Neural network-based video compression takes two forms: neural network-based encoding / decoding tools and end-to-end neural network-based video compression. The former is embedded as an encoding / decoding tool within a classical video codec, serving only as part of the framework; while the latter is a separate framework developed based on neural networks, independent of classical video codecs.

[0029] A series of classic video codec standards have been developed to accommodate the ever-increasing amount of visual content. The International Organization for Standardization (ISO) / International Electrotechnical Commission (IEC) has two expert groups, the Joint Group of Picture Experts (JPEG) and the Moving Picture Experts Group (MPEG), and the International Telecommunication Union (ITU) Telecommunication Standardization Sector (ITU-T) also has its own Video Codec Experts Group (VCEG) for standardizing image or video codec technologies. Influential video codec standards released by these organizations include JPEG, JPEG 2000, H.262, H.264 / Advanced Video Codec (AVC), and H.265 / High-Efficiency Video Codec (HEVC). Following H.265 / HEVC, the Joint Video Experts Group (JVET), comprised of MPEG and VCEG, began working on the video codec standard Multifunctional Video Codec (VVC). The first version of VVC was released in July 2020. It has been reported that, compared to HEVC, VVC reduces the bit rate by an average of 50% while maintaining the same visual quality.

[0030] Many researchers have focused on neural network-based image encoding and decoding for use in neural network-based image / video compression. However, the network architectures used in example designs are relatively shallow, resulting in unsatisfactory performance. Thanks to abundant data and powerful computing resources, neural network-based methods have been better utilized in various applications. Currently, neural network-based image / video compression has shown promising improvements and demonstrated its feasibility. However, this technology is far from mature, and many challenges remain to be addressed.

[0031] 2.2. Neural Networks

[0032] Neural networks, also known as artificial neural networks (ANNs), are computational models used in machine learning techniques. They typically consist of multiple processing layers, each composed of several simple but non-linear basic computational units. One advantage of these deep networks is their ability to process data with multiple levels of abstraction and transform the data into different kinds of representations. Note that these representations are not manually designed; instead, they are learned from massive amounts of data using general machine learning procedures. Deep learning eliminates the need for manually designed representations and is therefore considered particularly suitable for processing natively unstructured data, such as acoustic and visual signals, which has been a long-standing challenge in the field of artificial intelligence.

[0033] 2.3. Neural Networks for Image and Video Compression

[0034] Example neural networks used in image compression methods can be divided into two categories: pixel probability modeling and autoencoders. The former belongs to predictive encoding / decoding strategies, while the latter is a transform-based solution. Sometimes, these two methods are combined.

[0035] Similar to classic video encoding and decoding techniques, neural image compression is based on intra-frame compression in neural network-based video compression. Therefore, the development of neural network-based video compression technology lagged behind that of neural network-based image compression, but due to its complexity, it requires more effort to overcome the challenges. Some researchers are working on neural network-based video compression schemes. Compared to image compression, video compression requires effective methods to remove inter-frame redundancy. Inter-frame prediction is a key step in these works. Motion estimation and compensation have been employed, but only recently have they been implemented using trained neural networks.

[0036] Neural network-based video compression research can be divided into two categories based on the target scenario: random access and low latency. In the case of random access, decoding can begin at any point in the sequence, dividing the entire sequence into multiple separate segments, each of which can be decoded independently. The low latency approach aims to reduce decoding time, allowing earlier frames to be used as reference frames for decoding subsequent frames.

[0037] 2.4. Signaling for JPEG AI Image Encoding / Decoding Standards and Rendering Information

[0038] The JPEG AI image codec standard is an image codec standard managed by the JPEG Working Group (WG), which is WG 1 of ISO / IEC Joint Technical Committee (JTC) 1 SC 29. The ISO / IEC number for the JPEG AI standard is ISO / IEC 6048.

[0039] The example JPEG AI draft specification utilizes some of the neural network-based image encoding and decoding methods described above. Some features of the example JPEG AI specification, as well as the signaling methods used for rendering information, are described or summarized below. Rendering information includes code point rendering information independent of encoding / decoding (CICP), mastering display color volume information, content light level information, and dynamic metadata.

[0040] 2.4.1. (6.2) Stream Layout ...

[0042] The bitstream consists of seven parts with byte boundaries, namely:

[0043] 1. Start of Stream (SOC) marker;

[0044] 2. Image header marker (PIH), followed by the image header;

[0045] 3. Tool Header Mark (TOH), followed by tool information;

[0046] 4. Rendering Information Header (RIH), followed by rendering information;

[0047] 5. Start of Quality Quote (SOQ), followed by the bitstream;

[0048] 6. The Z-stream starts with a Start of Z (SOZ) marker, followed by the bitstream of the super-prior information tensor z, including... and ;

[0049] 7. The residual stream start marker (SORp) of the primary component, followed by the bitstream of the primary component residual, including... ;

[0050] 8. Start marks (SORs) of the residual stream of the secondary component, followed by the bitstream of the secondary component residual, including... ;

[0051] 9. End of stream (EOC) marker.

[0052] The overall grammatical structure of the image is as follows:

[0053]

[0054] Each bitstream begins with a 16-bit marker. All markers used in this specification are as follows:

[0055] ...

[0057] 2.4.2. (6.3) Image header

[0058] This substream contains information about the image height. ,width Potential space piece location and size, control flags for each tool, scaling factors for primary and secondary components, - Learnable model index and displacement (primary components) for rate control parameters Secondary components are (information).

[0059] 2.4.2.1 (9.3.1) Syntax Table

[0060] ...

[0062] 2.4.2.3. (6.3.2) Image header semantics

[0063] The following service information is transmitted via signal:

[0064] picture_header_size is the number of bytes in the image header excluding the first two bytes of the marker;

[0065] Adding 64 to img_width specifies the width of the input image (from 64 to 65599).

[0066] img_height plus 64 specifies the height of the input image (from 64 to 65599); ...

[0068] 2.4.3 (6.5) Rendering the header information

[0069] This optional substream contains information about rendering.

[0070] Rendering header syntax table

[0071]

[0072] Code points unrelated to encoding and decoding

[0073]

[0074] Mastering display color volume

[0075]

[0076] Content brightness level information

[0077]

[0078] Dynamic metadata

[0079]

[0080] Rendering information semantics

[0081] The `colour_primaries` parameter carries the `ColourPrimaries` value as defined in ISO / IEC 23091-2. The default value must be 1, which is the same as the primary color defined in ITU-R BT.709.

[0082] The `transfer_characteristics` parameter carries the `TransferCharacteristics` value as defined in ISO / IEC 23091-2. The default value must be 13. If `matrix_coefficients` equals 0, the transfer characteristics with a value of 13 are the same as those defined in the IEC 61966-2-1 standard for red, green, and blue (sRGB).

[0083] matrix_coefficients carries the MatrixCoefficients value as defined in ISO / IEC 23091-2. The default value must be 1, which is the same as the matrix coefficients defined in ITU-R BT.709.

[0084] The `image_full_range_flag` carries the `VideoFullRangeFlag` as defined in ISO / IEC 23091-2. The default value must be 1, meaning the image utilizes the full range.

[0085] `chroma420_sample_loc_type` carries the `Chroma420SampleLocType` as defined in ISO / IEC 23091-2. The default value must be 2, which means that the chroma and luminance samples are located in the same position without horizontal or vertical offset.

[0086] When mastering_display_colour_primaries_x[i] is in the range of 5 to 37000 (inclusive), it specifies the normalized x-chromatic coordinates of the primary color components i of the master display, in increments of 0.00002 according to the International Commission on Illumination (CIE) 1931 definition of x as specified in ISO 11664-1.

[0087] When mastering_display_colour_primaries_y[i] is in the range of 5 to 42000 (inclusive), it specifies the normalized x-chromaticity coordinates of the primary color components i of the master display, in increments of 0.00002 according to the definition of x in CIE 1931 as specified in ISO 11664-1.

[0088] When mastering_display_white_point_chromaticity_x is in the range of 5 to 37000 (inclusive), it specifies the normalized x-chromaticity coordinates of the white point of the master display, in normalization increments of 0.00002 according to the definition of x in CIE 1931 as specified in ISO 11664-1.

[0089] When mastering_display_white_point_chromaticity_y is in the range of 5 to 42000 (inclusive), it specifies the normalized x-chromaticity coordinates of the white point of the master display, in normalization increments of 0.00002 according to the definition of x in CIE 1931 as specified in ISO 11664-1.

[0090] When mastering_display_maximum_luminance is in the range of 50,000 to 100,000,000, it specifies the nominal maximum display brightness of the master display, in units of 0.0001 candela per square meter.

[0091] When `mastering_display_minimum_luminance` is in the range of 1 to 50000, it specifies the nominal minimum display brightness of the master display, expressed in 0.0001 candela per square meter. When `mastering_display_maximum_luminance` is equal to 50000, `mastering_display_minimum_luminance` should not be equal to 50000.

[0092] When not equal to 0, maximum_content_light_level indicates the upper limit of the maximum brightness among all individual samples in the 4:4:4 representation of the red, green, and blue primal color intensities of the image (in the linear light domain), in candela per square meter.

[0093] When not equal to 0, maximum_frame_average_light_level indicates the upper limit of the maximum average brightness between samples in a 4:4:4 representation of the red, green, and blue primary color intensities (in the linear light domain) of any single image, in candela per square meter.

[0094] last_payload_size_byte is the last byte of the payload size of the dynamic metadata.

[0095] dynamic_metadata_payload_byte must be bytes containing data registered as specified in Recommendation ITU-T T.35. ...

[0097] 3. The technical problem solved by the disclosed technical solution

[0098] The example design for signaling of JPEG AI rendering information has the following problems:

[0099] First, the syntax and semantics of the render header, which includes the render header tag, are inconsistent because the syntax specifies that the render header, which includes the render header tag, is not optional, while the semantics state that it is optional.

[0100] Second, it involves four types of rendering information: code point (CICP) rendering information independent of encoding / decoding, color volumetric information for mastering displays, content brightness level information, and dynamic metadata. However, it is not possible to transmit some of these types of rendering information via signaling while omitting the others.

[0101] Third, the number of bits in the syntax structure of CICP rendering information is not an integer number of bytes.

[0102] Fourth, the syntax used for dynamic metadata signaling lacks an indication of the dynamic metadata type. For example, one type of dynamic metadata is called ST 2094-10 data, which is specified in SMPTE Standards Technology (ST) 2094-10 “Dynamic Metadata for Color Volume Transform - Application #1” and several other standard specifications (such as ETSI TS 103 572, High Dynamic Range (HDR) Signalling and Carriage of Dynamic Metadata for Color Volume Transform; Application #1).

[0103] Fifth, the syntax for dynamic metadata signaling is not intuitive, and the payload size signaling is inefficient when the size is greater than 256 bytes, and the efficiency decreases as the size increases.

[0104] 4. List of solutions and implementation examples

[0105] To address the aforementioned problems, methods outlined below are disclosed. These aspects should be considered as examples for interpreting general concepts, and not interpreted in a narrow sense. Furthermore, these examples can be applied individually or in any combination.

[0106] 1) In one example, in a JPEG AI stream, rendering information (including one or more of the following: code point rendering information independent of encoding / decoding (CICP), mastering display color volume information, content brightness level information, and dynamic metadata) is transmitted via signals in the rendering information syntax structure, and the rendering information syntax structure is directly included in the image header.

[0107] a. In one example, in addition, the render information header tag syntax elements are not signaled in the render information syntax structure.

[0108] 2) In one example, in a JPEG AI stream, it is permissible to transmit only some types of rendering information via signaling, such as code point (CICP) rendering information independent of encoding / decoding, mastering display color volume information, content brightness level information, and one or more but not all of dynamic metadata, without transmitting other types of rendering information via signaling.

[0109] a. In one example, for a specific type of rendering information, an indication is included in the JPEG AI stream to indicate whether that specific type of rendering information exists.

[0110] i. In one example, for each of the four types of rendering information, an indication is included in the JPEG AI stream to indicate whether that particular type of rendering information exists.

[0111] 3) In one example, the syntax structure of CICP rendering information consists of an integer number of bytes.

[0112] a. In one example, a 7-bit syntax element (e.g., named cicp_reserved_zero_7bits) is included in the syntax structure of the CICP rendering information, immediately following the image_full_range_flag syntax element.

[0113] i. In one example, optionally, a 7-bit syntax element (e.g., named cicp_reserved_zero_7bits) is included in the syntax structure of the CICP rendering information, immediately preceding the image_full_range_flag syntax element.

[0114] 4) In one example, in a JPEG AI stream, dynamic metadata rendering information is transmitted via signaling through a syntax structure consisting of an indicator of the dynamic metadata type, an indicator of the dynamic metadata size, and data bytes of the dynamic metadata, preferably in the order listed.

[0115] a. In one example, the dynamic metadata type is indicated by an 8-bit syntax element (e.g., named dm_type).

[0116] i. In one example, specifying dm_type equal to a specific value (e.g., 0) indicates that the dynamic metadata is the ST2094-10_data() structure as specified in ETSI TS103572 V1.3.1.

[0117] ii. In one example, it is specified that some values ​​of dm_type are reserved for future use.

[0118] iii. In one example, it is specified that for JPEG AI bitstreams conforming to this version of the standard, the value of dm_type must be equal to 0.

[0119] iv. In one example, it is specified that when encountering a dm_type greater than 0, the decoder conforming to this version of the standard must ignore the dynamic_metadata() syntax structure.

[0120] b. In one example, the size of the dynamic metadata is indicated by a 16-bit syntax element.

[0121] i. In one example, the size of dynamic metadata is indicated by an 8-bit syntax element.

[0122] ii. In one example, the length of the syntax element indicating the size of dynamic metadata is indicated by another syntax element (e.g., a 1-bit or 2-bit syntax element).

[0123] 5) In one example, in a JPEG AI stream, rendering information (including one or more of the following: code point rendering information independent of encoding / decoding (CICP), mastering display color volume information, content brightness level information, and dynamic metadata) is transmitted via signals in a rendering information syntax structure, and the rendering information syntax structure is directly included in the picture() syntax structure, wherein the existence of the rendering information syntax structure depends on whether the value of the next M bits following another syntax structure that is directly present in the picture() syntax structure is equal to the value of the rendering information tag.

[0124] a. In one example, M equals 16, and the value of the rendering information tag is 0xff84.

[0125] 6) In one example, based on item 1 or 5 above, within the rendering information syntax structure, there is an N-bit syntax element SE_1 indicating the length (in bytes) of another syntax element SE_2, the number of presence flags indicating the presence of different types of rendering information, the number of reserved bits, and a syntax element SE_2, wherein the syntax element SE_2 indicates the size (in bytes) of all remaining data in the rendering information syntax structure after the last of SE_1, presence flags, reserved bits, and SE_2.

[0126] a. In one example, the sum of N, the number of presence flags, and the number of reserved bits is an integer multiple of 8.

[0127] b. In one example, the sum of N, the number of presence flags, and the number of reserved bits equals 8.

[0128] c. In one example, N is 2, the number of presence flags is 4, and the number of reserved bits is 2, and the values ​​of SE_1 0, 1, 2, and 3 indicate that the length of SE_2 is 1, 2, 3, and 4 bytes, respectively.

[0129] 7) In one example, based on item 1 or 5 above, within the rendering information syntax structure, there is an X-bit syntax element SE_1 indicating the size (in bytes) of all remaining data after the last one in SE_1, and the number of presence flags indicating the presence of CICP rendering information, master production display color volume information, content brightness level information, and dynamic metadata, wherein the sum of X and the number of presence flags (e.g., 4) is an integer multiple of 8.

[0130] a. In one example, X equals 24.

[0131] 8) In one example, based on item 1 or 5 above, CICP rendering information is included in the CICP rendering information syntax structure, and within the CICP rendering information syntax structure, syntax elements carrying Chroma420SampleLocType as defined in ISO / IEC 23091-2 are encoded and decoded using 3 bits (3).

[0132] a. In one example, optionally, syntax elements carrying Chroma420SampleLocType as defined in ISO / IEC 23091-2 are encoded and decoded using 4 bits in u(4).

[0133] 9) In one example, based on item 1 or 5 above, CICP rendering information is included in the CICP rendering information syntax structure, and the CICP rendering information syntax structure contains a syntax element SE_3 carrying Chroma420SampleLocType as defined in ISO / IEC 23091-2, which specifies that when the chroma format is not 4:2:0, the semantics of SE_3 are not specified, and the decoder must ignore the value of SE_3.

[0134] a. In one example, optionally, the syntax element SE_3 is conditionally transmitted via signaling and exists only in the CICP rendering information syntax structure if the chroma format is 4:2:0.

[0135] 10) In one example, based on item 8 or 9 above, zero or more byte alignment bits are appended to the end of the CICP rendering information syntax structure until the total number of bits in the CICP rendering information syntax structure is an integer multiple of 8.

[0136] 11) In one example, based on item 1 or 5 above, zero or more byte alignment bits are appended to the end of the rendering information syntax structure until the total number of bits in the rendering information syntax structure is an integer multiple of 8.

[0137] 5. Examples

[0138] The following are some example implementations of the aspects outlined in Chapter 4 above.

[0139] 5.1 First Embodiment

[0140] This embodiment applies to all items 1, 1.a, 2, 2.a, 2.ai, 3, 3.a, 4, 4.a, 4.ai, 4.a.ii, 4.a.iii, 4.a.iv and 4.b outlined in Section 4 above.

[0141] 5.1.1. (6.2) Stream Layout ...

[0143] The bitstream consists of six parts with byte boundaries:

[0144] 1. Start of stream marker (SOC);

[0145] 2. Image header marker (PIH), followed by the image header;

[0146] 3. Tool Header Mark (TOH), followed by tool information;

[0147] 4. Start of Quality Quote (SOQ), followed by the bitstream;

[0148] 5. The Z-stream starts with a Start of Z (SOZ) marker, followed by the bitstream of the super-prior information tensor z, including... and ;

[0149] 6. The residual stream begins with the primary component marker (SORp), followed by the bitstream of the primary component residual, including... ;

[0150] 7. The secondary component-marked residual stream begins (SORs), followed by the bitstream of the secondary component residuals, including... ;

[0151] 8. End of stream marker (EOC).

[0152] The overall grammatical structure of the image is as follows:

[0153]

[0154] Each bitstream begins with a 16-bit marker. All markers used in this specification are as follows:

[0155]

[0156] 5.1.2. (6.3) Image header

[0157] This substream contains information about the image height. ,width Potential space piece location and size, control flags for each tool, scaling factors for primary and secondary components, - Learnable model index and displacement (primary components) for rate control parameters Secondary components are (information).

[0158] 2.4.2.1 (9.3.1) Syntax Table

[0159] ...

[0161] 2.4.2.3 (6.3.2) Image header semantics

[0162] The following service information is transmitted via signal:

[0163] picture_header_size is the number of bytes in the image header excluding the first two bytes of the marker;

[0164] The img_width parameter plus 64 specifies the width of the input image (from 64 to 65599).

[0165] img_height plus 64 specifies the height of the input image (from 64 to 65599); ...

[0167] 5.1.3 (6.5) Rendering Information

[0168] Rendering information syntax

[0169]

[0170] CICP rendering information

[0171]

[0172] Mastering display color volume

[0173]

[0174] Content brightness level information

[0175]

[0176] Dynamic metadata

[0177]

[0178] Rendering information semantics

[0179] A cicp_info_present_flag value of 1 indicates the existence of the cicp_rendering_info() syntax structure. A cicp_info_present_flag value of 0 indicates the non-existence of the cicp_rendering_info() syntax structure.

[0180] A value of 1 for `mdcv_info_present_flag` indicates the existence of the `mastering_display_color_volume()` syntax structure. A value of 0 for `mdcv_info_present_flag` indicates the absence of the `mastering_display_color_volume()` syntax structure.

[0181] A cll_info_present_flag value of 1 indicates the existence of the content_light_level_info() syntax structure. A cll_info_present_flag value of 0 indicates the non-existence of the content_light_level_info() syntax structure.

[0182] A value of 1 for `dm_present_flag` indicates the existence of the `dynamic_metadata()` syntax structure. A value of 0 for `dm_present_flag` indicates the absence of the `dynamic_metadata()` syntax structure.

[0183] In JPEG bitstreams conforming to this version of the standard, ri_reserved_zero_4bits must be equal to 0. Values ​​of ri_reserved_zero_4bits greater than 0 are reserved for future use by ISO / IEC. When encountering ri_reserved_zero_4bits greater than 0, decoders conforming to this version of the standard must ignore the ri_reserved_zero_4bits syntax element.

[0184] colour_primaries carries ColourPrimaries values ​​as defined in ISO / IEC 23091-2. When cicp_info_present_flag equals 0, the default value of colour_primaries is presumed to be 1, which is the same as the color primary colors defined in ITU Recommendation 709 for Broadcast Television Services (ITU-R BT.709).

[0185] The `transfer_characteristics` parameter carries the `TransferCharacteristics` value as defined in ISO / IEC 23091-2. When `cicp_info_present_flag` equals 0, the default value for `transfer_characteristics` is presumed to be 13. When `matrix_coefficients` equals 0, the transfer characteristic with a value of 13 is the same as that defined in IEC 61966-2-1 sRGB.

[0186] matrix_coefficients carries the MatrixCoefficients value as defined in ISO / IEC 23091-2. When cicp_info_present_flag equals 0, the default value of matrix_coefficients is presumed to be 1, which is the same as the matrix coefficients defined in ITU-R BT.709.

[0187] The `image_full_range_flag` carries the `VideoFullRangeFlag` as defined in ISO / IEC 23091-2. When `cicp_info_present_flag` is equal to 0, the default value of `image_full_range_flag` is presumed to be 1, which means that the image utilizes the full range.

[0188] In JPEG bitstreams conforming to this version of the standard, cicp_reserved_zero_7bits must be equal to 0. Values ​​greater than 0 for cicp_reserved_zero_7bits are reserved for future use by ISO / IEC. When encountering a cicp_reserved_zero_7bits value greater than 0, decoders conforming to this version of the standard must ignore the cicp_reserved_zero_7bits syntax element.

[0189] chroma420_sample_loc_type carries the Chroma420SampleLocType as defined in ISO / IEC 23091-2. When cicp_info_present_flag equals 0, the default value of chroma420_sample_loc_type is presumed to be 2, which means that the chroma samples and the luminance samples are located in the same position without horizontal or vertical offset.

[0190] When mastering_display_colour_primaries_x[i] is in the range of 5 to 37000 (inclusive), it specifies the normalized x chromaticity coordinates of the primary color components i of the master display, in increments of 0.00002 according to the definition of x in CIE 1931 as specified in ISO 11664-1.

[0191] When mastering_display_colour_primaries_y[i] is in the range of 5 to 42000 (inclusive), it specifies the normalized x-chromaticity coordinates of the primary color components i of the master display, in increments of 0.00002 according to the definition of x in CIE 1931 as specified in ISO 11664-1.

[0192] When mastering_display_white_point_chromaticity_x is in the range of 5 to 37000 (inclusive), it specifies the normalized x-chromaticity coordinates of the white point of the master display, in normalization increments of 0.00002 according to the definition of x in CIE 1931 as specified in ISO 11664-1.

[0193] When mastering_display_white_point_chromaticity_y is in the range of 5 to 42000 (inclusive), it specifies the normalized x-chromaticity coordinates of the white point of the master display, in normalization increments of 0.00002 according to the definition of x in CIE 1931 as specified in ISO 11664-1.

[0194] `mastering_display_maximum_luminance` specifies the nominal maximum display brightness of the master display when it is in the range of 50,000 to 100,000,000, in units of 0.0001 candela per square meter.

[0195] When `mastering_display_minimum_luminance` is in the range of 1 to 50000, it specifies the nominal minimum display brightness of the master display, expressed in 0.0001 candela per square meter. When `mastering_display_maximum_luminance` is equal to 50000, `mastering_display_minimum_luminance` should not be equal to 50000.

[0196] When not equal to 0, maximum_content_light_level indicates the upper limit of the maximum brightness among all individual samples in the 4:4:4 representation of the red, green, and blue primal color intensities of the image (in the linear light domain), in candela per square meter.

[0197] When not equal to 0, maximum_frame_average_light_level indicates the upper limit of the maximum average brightness between samples in a 4:4:4 representation of the red, green, and blue primary color intensities (in the linear light domain) of any single image, in candela per square meter.

[0198] `dm_type` specifies the type of dynamic metadata. A `dm_type` of 0 indicates that the dynamic metadata carried by `dm_data_byte[i]` within the range of 0 to `dm_size - 1` (inclusive) is the `ST2094-10_data()` structure as specified in European Telecommunications Standards Institute (ETSI) Technical Specification (TS) 103572 V1.3.1. For JPEG AI bitstreams conforming to this version of the standard, the value of `dm_type` must be 0. Values ​​of `dm_type` greater than 0 are reserved for future use by ISO / IEC. When `dm_type` is greater than 0, decoders conforming to this version of the standard must ignore the `dynamic_metadata()` syntax structure.

[0199] dm_size specifies the number of bytes for dynamic metadata.

[0200] dm_data_byte[i] is the i-th byte of the dynamic metadata.

[0201] 5.2 Second Embodiment

[0202] This embodiment applies to all items 5, 5.a, 6, 6.a, 6.b, 6.c, 8, and 9 outlined in Section 4 above.

[0203] 5.2.1. (2.2) Specification of Syntax Functions and Descriptors

[0204] The functions presented here are used for syntax description. These functions are expressed based on the value of a bitstream pointer, which indicates the position of the next bit to be read from the bitstream by the decoding process.

[0205] The `read_bits(n)` function reads the next `n` bits from the bitstream and moves the bitstream pointer forward by `n` bits. When `n` equals 0, `read_bits(n)` returns 0 and does not move the bitstream pointer.

[0206] The `read_bits_from_back(n)` function reads `n` bits from the end of a substream in the bitstream and moves the substream bitstream pointer forward by `n` bits. When `n` equals 0, `read_bits_from_back(n)` returns 0 and does not move the substream bitstream pointer.

[0207] The next_bits(n) function provides the next bit in the bitstream for comparison without moving the bitstream pointer.

[0208] The following descriptors specify the parsing process for each syntax element:

[0209] - b(8): Bytes (8 bits) of any pattern with a bit string. The parsing process for this descriptor is specified by the return value of the function read_bits(8).

[0210] - f(n): A fixed-pattern bit string of n bits, written (from left to right) with the leftmost bit first. The parsing process for this descriptor is specified by the return value of the function read_bits(n).

[0211] - i(n): A signed integer using n bits. When n is "v" in the syntax table, the number of bits varies in a manner that depends on the values ​​of other syntax elements. The parsing process for this descriptor is specified by the return value of the function read_bits(n), which is interpreted as a two's complement integer representation, with the most significant bit written first.

[0212] - se(v): A syntax element for signed integer zero-order Exp-Golomb encoding / decoding, with the left bit first. The parsing procedure for this descriptor is specified in Appendix C, where the order k equals 0.

[0213] - u(n): An unsigned integer using n bits. When n is "v" in the syntax table, the number of bits varies in a manner that depends on the values ​​of other syntax elements. The parsing process for this descriptor is specified by the return value of the function read_bits(n), which is interpreted as a binary representation of the unsigned integer, with the most significant bit written first.

[0214] - ub(n): An unsigned integer using n bits. When n is "v" in the syntax table, the number of bits varies in a manner that depends on the values ​​of other syntax elements. The parsing process for this descriptor is specified by the return value of the function read_bits_from_back(n), which is interpreted as a binary representation of the unsigned integer, with the most significant bit written first.

[0215] 5.2.2. (6.2) Stream Layout ...

[0217] The bitstream consists of seven parts with byte boundaries, namely:

[0218] 1. SOC - Start of Stream Marker;

[0219] 2. PIH (Picture Header Marker), followed by the image header;

[0220] 3. TOH (Tool Head Marker), followed by tool information;

[0221] 4. RDI (Rendering Information Markup), followed by rendering information;

[0222] 5. SOQ (Start of Quality Graph), followed by the bitstream;

[0223] 6. SOZ (Start of Z-stream marker), followed by the bitstream of the super-prior information tensor z, including... and ;

[0224] 7. SORp (start of residual stream marked by major component), followed by the bitstream of the major component residual, including... ;

[0225] 8. SORs (start of residual stream marked by minor component), followed by the bitstream of the minor component residual, including... ;

[0226] 9. EOC - End of stream marker.

[0227] The overall grammatical structure of the image is as follows:

[0228]

[0229] Each bitstream begins with a 16-bit marker. All markers used in this specification are as follows:

[0230]

[0231] When the SOQ flag exists and a second flag with a value in the range of 0xff83 to 0xff84 (inclusive) also exists, the substream associated with the second flag must precede the quality map substream associated with the SOQ flag in the decoder order.

[0232] 5.2.3. (6.3) Image header

[0233] This substream contains information about the image height. ,width Potential space piece location and size, control flags for each tool, scaling factors for primary and secondary components, - Learnable model index and displacement (primary components) for rate control parameters Secondary components are (information).

[0234] 2.4.2.1 (9.3.1) Syntax Table

[0235] ...

[0237] 2.4.2.3 (6.3.2) Image header semantics

[0238] The following service information is transmitted via signal:

[0239] picture_header_size is the number of bytes in the image header excluding the first two bytes of the marker;

[0240] Adding 64 to img_width specifies the width of the input image (from 64 to 65599).

[0241] img_height plus 64 specifies the height of the input image (from 64 to 65599); ...

[0243] 5.2.4. (6.5) Rendering Information

[0244] Rendering information syntax

[0245]

[0246] CICP rendering information

[0247]

[0248] Mastering display color volume

[0249]

[0250] Content brightness level information

[0251]

[0252] Dynamic metadata

[0253]

[0254] Rendering information semantics

[0255] The increment of 1 in ri_payload_size_len_in_bytes_minus1 specifies the number of bytes used to represent the syntax element ri_payload_size_val.

[0256] A cicp_info_present_flag value of 1 indicates the existence of the cicp_rendering_info() syntax structure. A cicp_info_present_flag value of 0 indicates the non-existence of the cicp_rendering_info() syntax structure.

[0257] A value of 1 for `mdcv_info_present_flag` indicates the existence of the `mastering_display_color_volume()` syntax structure. A value of 0 for `mdcv_info_present_flag` indicates the absence of the `mastering_display_color_volume()` syntax structure.

[0258] A cll_info_present_flag value of 1 indicates the existence of the content_light_level_info() syntax structure. A cll_info_present_flag value of 0 indicates the non-existence of the content_light_level_info() syntax structure.

[0259] A value of 1 for `dm_present_flag` indicates the existence of the `dynamic_metadata()` syntax structure. A value of 0 for `dm_present_flag` indicates the absence of the `dynamic_metadata()` syntax structure.

[0260] When the rendering_information() syntax structure exists in the picture() syntax structure, at least one of cicp_info_present_flag, mdcv_info_present_flag, cll_info_present_flag, and dm_present_flag must be equal to 1.

[0261] In JPEG AI streams conforming to this version of the standard, ri_reserved_zero_2bits must be equal to 0. Values ​​of ri_reserved_zero_2bits greater than 0 are reserved for future use by ISO / IEC. When encountering ri_reserved_zero_2bits greater than 0, decoders conforming to this version of the standard must ignore the ri_reserved_zero_2bits syntax element.

[0262] The `ri_payload_size_val` parameter specifies the size of the rendering information substream payload in bytes (i.e., the substream excludes the syntax elements starting from the RDI marker up to and including `ri_payload_size_val`). The `ri_payload_size_val` syntax element is represented by `ri_payload_size_len_in_bytes_minus1 + 1` bytes.

[0263] colour_primaries carries ColourPrimaries values ​​as defined in ISO / IEC 23091-2. When cicp_info_present_flag equals 0, the default value of colour_primaries is presumed to be 1, which is the same as the primary colors defined in ITU-R BT.709.

[0264] The `transfer_characteristics` parameter carries the `TransferCharacteristics` value as defined in ISO / IEC 23091-2. When `cicp_info_present_flag` equals 0, the default value for `transfer_characteristics` is presumed to be 13. When `matrix_coefficients` equals 0, the transfer characteristic with a value of 13 is the same as that defined in IEC 61966-2-1 sRGB.

[0265] matrix_coefficients carries the MatrixCoefficients value as defined in ISO / IEC 23091-2. When cicp_info_present_flag equals 0, the default value of matrix_coefficients is presumed to be 1, which is the same as the matrix coefficients defined in ITU-R BT.709.

[0266] The `image_full_range_flag` carries the `VideoFullRangeFlag` as defined in ISO / IEC 23091-2. When `cicp_info_present_flag` is equal to 0, the default value of `image_full_range_flag` is presumed to be 1, which means that the image utilizes the full range.

[0267] When the chroma format is not 4:2:0, `chroma420_sample_loc_type` carries `Chroma420SampleLocType` as defined in ISO / IEC 23091-2. When `cicp_info_present_flag` equals 0, the default value of `chroma420_sample_loc_type` is presumed to be 2, meaning that chroma and luma samples are located in the same position without horizontal or vertical offset. When the chroma format is not 4:2:0, the semantics of `chroma420_sample_loc_type` are not specified, and the decoder must ignore the value of `chroma420_sample_loc_type`.

[0268] In JPEG AI streams conforming to this version of the standard, cicp_reserved_zero_4bits must be equal to 0. Values ​​greater than 0 for cicp_reserved_zero_4bits are reserved for future use by ISO / IEC. When encountering a cicp_reserved_zero_4bits value greater than 0, decoders conforming to this version of the standard must ignore the cicp_reserved_zero_4bits syntax element.

[0269] When mastering_display_colour_primaries_x[i] is in the range of 5 to 37000 (inclusive), it specifies the normalized x chromaticity coordinates of the primary color components i of the master display, in increments of 0.00002 according to the definition of x in CIE 1931 as specified in ISO 11664-1.

[0270] When mastering_display_colour_primaries_y[i] is in the range of 5 to 42000 (inclusive), it specifies the normalized x-chromaticity coordinates of the primary color components i of the master display, in increments of 0.00002 according to the definition of x in CIE 1931 as specified in ISO 11664-1.

[0271] When mastering_display_white_point_chromaticity_x is in the range of 5 to 37000 (inclusive), it specifies the normalized x-chromaticity coordinates of the white point of the master display, in normalization increments of 0.00002 according to the definition of x in CIE 1931 as specified in ISO 11664-1.

[0272] When mastering_display_white_point_chromaticity_y is in the range of 5 to 42000 (inclusive), it specifies the normalized x-chromaticity coordinates of the white point of the master display, in normalization increments of 0.00002 according to the definition of x in CIE 1931 as specified in ISO 11664-1.

[0273] When mastering_display_maximum_luminance is in the range of 50,000 to 100,000,000, it specifies the nominal maximum display brightness of the master display, in units of 0.0001 candela per square meter.

[0274] When `mastering_display_minimum_luminance` is in the range of 1 to 50000, it specifies the nominal minimum display brightness of the master display, in units of 0.0001 candela per square meter. When `mastering_display_maximum_luminance` is equal to 50000, `mastering_display_minimum_luminance` should not be equal to 50000.

[0275] When not equal to 0, maximum_content_light_level indicates the upper limit of the maximum brightness among all individual samples in the 4:4:4 representation of the red, green, and blue primal color intensities of the image (in the linear light domain), in candela per square meter.

[0276] When not equal to 0, maximum_frame_average_light_level indicates the upper limit of the maximum average brightness between samples in a 4:4:4 representation of the red, green, and blue primary color intensities (in the linear light domain) of any single image, in candela per square meter.

[0277] `dm_type` specifies the type of dynamic metadata. A `dm_type` of 0 indicates that the dynamic metadata carried by `dm_data_byte[i]` within the range of 0 to `dm_size - 1` (inclusive) is the `ST2094-10_data()` structure as specified in ETSI TS 103572 V1.3.1. For JPEG AI bitstreams conforming to this version of the standard, the value of `dm_type` must be 0. Values ​​of `dm_type` greater than 0 are reserved for future use by ISO / IEC. When encountering a `dm_type` greater than 0, decoders conforming to this version of the standard must ignore the `dynamic_metadata()` syntax structure.

[0278] dm_size specifies the number of bytes for dynamic metadata.

[0279] dm_data_byte[i] is the i-th byte of the dynamic metadata.

[0280] Figure 1 This is a block diagram illustrating an example video processing system 4000 in which various techniques disclosed herein may be implemented. Various implementations may include some or all of the components of system 4000. System 4000 may include an input 4002 for receiving video content. The video content may be received in a raw or uncompressed format, such as 8 or 10-bit multi-component pixel values, or it may be received in a compressed or encoded format. Input 4002 may represent a network interface, a peripheral bus interface, or a storage interface. Examples of network interfaces include wired interfaces such as Ethernet, Passive Optical Network (PON), and wireless interfaces such as Wi-Fi or cellular interfaces.

[0281] System 4000 may include an encoding component 4004 capable of implementing the various encoding / decoding or encoding methods described in this document. Encoding component 4004 can reduce the average bit rate from the video input 4002 to the output of encoding component 4004 to produce an encoded representation of the video. Encoding techniques are therefore sometimes referred to as video compression or video transcoding techniques. The output of encoding component 4004 may be stored or transmitted via a communication connection such as that represented by component 4006. The bitstream (or encoded) representation of the video received at input 4002, whether stored or transmitted via communication, may be used by component 4008 to generate pixel values ​​or displayable video to be transmitted to display interface 4010. The process of generating user-visible video from the bitstream representation is sometimes referred to as video decompression. Furthermore, although some video processing operations are referred to as “encoding” operations or tools, it is understood that encoding tools or operations are used by the encoder, and the corresponding decoding tools or operations that reverse the encoded result will be performed by the decoder.

[0282] Examples of peripheral bus interfaces or display interfaces may include Universal Serial Bus (USB), High Definition Multimedia Interface (HDMI), or DisplayPort. Examples of storage interfaces include Serial Advanced Technology Attachment (SATA), Peripheral Component Interconnect (PCI), and Integrated Drive Electronic Devices (IDE) interfaces. The technologies described in this document can be found in a variety of electronic devices, such as mobile phones, laptops, smartphones, or other devices capable of performing digital data processing and / or video display.

[0283] Figure 2This is a block diagram of an example video processing apparatus 4100. Apparatus 4100 can be used to implement one or more methods described herein. Apparatus 4100 can be embodied in a smartphone, tablet, computer, Internet of Things (IoT) receiver, etc. Apparatus 4100 may include one or more processors 4102, one or more memories 4104, and video processing circuitry 4106. The processors 4102(s) may be configured to implement one or more methods described herein. The memories 4104(s) may be used to store data and code for implementing the methods and techniques described herein. The video processing circuitry 4106 may be used to implement some of the techniques described herein in hardware circuitry. In some embodiments, the video processing circuitry 4106 may be at least partially included in the processor 4102, for example, a graphics coprocessor.

[0284] Figure 3 This is a flowchart of an example method 4200 for video processing. Method 4200 includes: in step 4202, determining that one or more of the following—code point (CICP) rendering information, mastering display color volume information, content brightness level information, and dynamic metadata—are included in a rendering information syntax structure in the image header of the Joint Group of Picture Experts (JPEG) Artificial Intelligence (AI) bitstream; and in step 4204, performing a conversion between visual media data and the JPEG AI bitstream based on the rendering information syntax structure. The conversion may include encoding at the encoder, decoding at the decoder, or a combination thereof.

[0285] It should be noted that method 4200 can be implemented in an apparatus for processing video data, including a processor and a non-transitory memory having instructions thereon, such as a video encoder 4400, a video decoder 4500, and / or an encoder 4600. In this case, the instructions cause the processor to perform method 4200 when executed by the processor. Furthermore, method 4200 can be executed by a non-transitory computer-readable medium including a computer program product for use by a video encoding / decoding device. The computer program product includes computer-executable instructions stored on the non-transitory computer-readable medium, such that when the computer-executable instructions are executed by a processor, the video encoding / decoding device performs method 4200.

[0286] Figure 4 This is a block diagram illustrating an example video encoding / decoding system 4300 that can utilize the techniques of this disclosure. The video encoding / decoding system 4300 may include a source device 4310 and a target device 4320. The source device 4310 generates encoded video data, wherein the source device 4310 may be referred to as a video encoding device. The target device 4320 can decode the encoded video data generated by the source device 4310, wherein the target device 4320 may be referred to as a video decoding device.

[0287] Source device 4310 may include video source 4312, video encoder 4314, and input / output (I / O) interface 4316. Video source 4312 may include sources such as video capture devices, interfaces for receiving video data from video content providers, and / or computer graphics systems for generating video data, or combinations thereof. Video data may include 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 forming a codec representation of the video data. The bitstream may include codec pictures and associated data. Codec pictures are codec representations of pictures. 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. Encoded video data may be transmitted directly to target device 4320 via network 4330 through I / O interface 4316. Encoded video data may also be stored on storage medium / server 4340 for access by target device 4320.

[0288] Target device 4320 may include I / O interface 4326, video decoder 4324, and 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 source device 4310 or 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 target device 4320 or may be external to target device 4320, wherein target device 4320 may be configured to interface with an external display device.

[0289] The video encoder 4314 and the video decoder 4324 can operate according to video compression standards, such as the High Efficiency Video Codec (HEVC) standard, the Multi-Functional Video Codec (VVM) standard, and other existing and / or further standards.

[0290] Figure 5 This is a block diagram illustrating an example of a video encoder 4400, which can be... Figure 4 The system 4300 shown includes a video encoder 4314. The video encoder 4400 can be configured to perform any or all of the techniques disclosed herein. The video encoder 4400 includes multiple functional components. The techniques described in this disclosure can be shared among the various components of the video encoder 4400. In some examples, a processor can be configured to perform any or all of the techniques described in this disclosure.

[0291] The functional components of the video encoder 4400 may include a segmentation unit 4401, a prediction unit 4402, 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 coding unit 4414. The prediction unit 4402 may include a mode selection unit 4403, a motion estimation unit 4404, a motion compensation unit 4405, and an intra-frame prediction unit 4406.

[0292] In other examples, the video encoder 4400 may include more, fewer, or different functional components. In one example, the prediction unit 4402 may include an intra-block copy (IBC) unit. The IBC unit can perform prediction in an IBC mode, where at least one reference picture is the picture in which the current video block is located.

[0293] Furthermore, some components such as the motion estimation unit 4404 and the motion compensation unit 4405 can be highly integrated, but for illustrative purposes, they are shown separately in the example of the video encoder 4400.

[0294] The segmentation unit 4401 can segment an image into one or more video blocks. The video encoder 4400 and the video decoder 4500 can support various video block sizes.

[0295] The mode selection unit 4403 can select one of several encoding / decoding modes (intra-frame encoding / decoding or inter-frame encoding / decoding), for example, based on error results, and provide the resulting intra-frame or inter-frame encoded / decoded block to the residual generation unit 4407 to generate residual block data, and to the reconstruction unit 4412 to reconstruct the coded block for use as a reference image. In some examples, the mode selection unit 4403 can select an intra-frame / inter-frame joint prediction (CIIP) mode, where prediction is based on inter-frame prediction signals and intra-frame prediction signals. In the case of inter-frame prediction, the mode selection unit 4403 can also select a resolution for the block based on motion vectors (e.g., sub-pixel precision or integer pixel precision).

[0296] To perform inter-frame prediction on the current video block, motion estimation unit 4404 can generate motion information for the current video block by comparing one or more reference frames from buffer 4413 with the current video block. Motion compensation unit 4405 can determine the predicted video block for the current video block based on the motion information and decoded samples of images from buffer 4413 other than the image associated with the current video block.

[0297] The motion estimation unit 4404 and the motion compensation unit 4405 can perform different operations on the current video block, for example, depending on whether the current video block is in an I-band, P-band, or B-band.

[0298] In some examples, motion estimation unit 4404 can perform unidirectional prediction on the current video block, and can search reference images in list 0 or list 1 to find a reference video block for the current video block. Motion estimation unit 4404 can then generate a reference index indicating the reference image in list 0 or list 1, which contains the reference video block and a motion vector indicating the spatial displacement between the current video block and the reference video block. Motion estimation unit 4404 can output the reference index, prediction direction indicator, and motion vector as motion information for the current video block. Motion compensation unit 4405 can generate a predicted video block for the current block based on the reference video block indicated by the motion information of the current video block.

[0299] In other examples, motion estimation unit 4404 can perform bidirectional prediction on the current video block. Motion estimation unit 4404 can search for reference images in list 0 to find a reference video block for the current video block, and can also search for reference images in list 1 to find another reference video block for the current video block. Motion estimation unit 4404 can then generate reference indices indicating the reference images containing the reference video blocks in lists 0 and 1, and motion vectors indicating the spatial displacement between the reference video blocks and the current video block. Motion estimation unit 4404 can output the reference index and motion vector of the current video block as motion information for the current video block. Motion compensation unit 4405 can generate a predicted video block for the current video block based on the reference video blocks indicated by the motion information of the current video block.

[0300] In some examples, the motion estimation unit 4404 can output a complete set of motion information for use in the decoder's decoding process. In some examples, the motion estimation unit 4404 may not output a complete set of motion information for the current video. Instead, the motion estimation unit 4404 can reference the motion information of another video block to transmit the motion information of the current video block via a signal. For example, the motion estimation unit 4404 may determine that the motion information of the current video block is sufficiently similar to the motion information of neighboring video blocks.

[0301] In one example, the motion estimation unit 4404 may indicate a value to the video decoder 4500 in the syntax structure associated with the current video block, which indicates that the current video block has the same motion information as another video block.

[0302] In another example, motion estimation unit 4404 may identify another video block and motion vector difference (MVD) in the syntax structure associated with the current video block. The motion vector difference indicates the difference between the motion vector of the current video block and the motion vector of the indicated video block. 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.

[0303] As discussed above, the video encoder 4400 can transmit motion vectors via signaling in a predictive manner. Two examples of predictive signaling techniques that can be implemented by the video encoder 4400 include Advanced Motion Vector Prediction (AMVP) and Merge Mode Signaling.

[0304] Intra-prediction unit 4406 can perform intra-prediction on the current video block. When intra-prediction unit 4406 performs intra-prediction on the current video block, it can generate prediction data for the current video block based on decoded samples of other video blocks in the same frame. The prediction data for the current video block can include the predicted video block and various syntax elements.

[0305] The residual generation unit 4407 can generate residual data for the current video block by subtracting (or more) predicted video blocks from the current video block. The residual data for the current video block may include residual video blocks corresponding to different sample components of the samples in the current video block.

[0306] In other examples, such as in skip mode, there may be no residual data for the current video block, and the residual generation unit 4407 may not perform subtraction operations.

[0307] The transform processing unit 4408 can generate one or more transform coefficient video blocks for the current video block by applying one or more transforms to the residual video blocks associated with the current video block.

[0308] After the transform processing unit 4408 generates a transform coefficient video block associated with the current video block, the quantization unit 4409 can 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.

[0309] The inverse quantization unit 4410 and the inverse transform unit 4411 can apply inverse quantization and inverse transform to the transform coefficient video block respectively to reconstruct the residual video block from the transform coefficient video block. The reconstruction unit 4412 can add the reconstructed residual video block to the corresponding sample points of one or more predicted video blocks generated by the prediction unit 4402 to generate a reconstructed video block associated with the current block and store it in the buffer 4413.

[0310] After the video block is reconstructed by reconstruction unit 4412, a loop filtering operation can be performed to reduce video block artifacts in the video block.

[0311] Entropy encoding unit 4414 can receive data from other functional components of video encoder 4400. When entropy encoding unit 4414 receives data, it can perform one or more entropy encoding operations to generate entropy-encoded data and output a bitstream including the entropy-encoded data.

[0312] Figure 6 This is a block diagram illustrating an example of a video decoder 4500, which can be... Figure 4 The system 4300 shown includes a video decoder 4324. The video decoder 4500 can be configured to perform any or all of the techniques disclosed herein. In the example shown, the video decoder 4500 includes multiple functional components. The techniques described in this disclosure can be shared among the various components of the video decoder 4500. In some examples, a processor can be configured to perform any or all of the techniques described in this disclosure.

[0313] In the example shown, the video decoder 4500 includes an entropy decoding unit 4501, a motion compensation unit 4502, an intra-frame prediction unit 4503, an inverse quantization unit 4504, an inverse transform unit 4505, a reconstruction unit 4506, and a buffer 4507. In some examples, the video decoder 4500 can perform a decoding process that is the overall inversion of the encoding process described with respect to the video encoder 4400.

[0314] The entropy decoding unit 4501 can retrieve the encoded bitstream. The encoded bitstream may include entropy-encoded video data (e.g., encoded blocks of video data). The entropy decoding unit 4501 can decode the entropy-encoded video data, and based on the entropy-decoded video data, the motion compensation unit 4502 can determine motion information including motion vectors, motion vector precision, reference image list index, and other motion information. The motion compensation unit 4502 can determine this information, for example, by executing AMVP and Merge modes.

[0315] The motion compensation unit 4502 can generate motion compensation blocks and can perform interpolation based on an interpolation filter. The identifier of the interpolation filter to be used with sub-pixel accuracy can be included in the syntax element.

[0316] The motion compensation unit 4502 can use interpolation filters, such as those used by the video encoder 4400 during the encoding of a video block, to calculate interpolations for sub-integer pixels of a reference block. The motion compensation unit 4502 can determine the interpolation filter used by the video encoder 4400 based on the received syntax information, and the motion compensation unit 4502 can use the interpolation filter to generate a prediction block.

[0317] The motion compensation unit 4502 may use some syntax information to determine the size of the blocks used to encode (multiple) frames and / or (multiple) stripes of the encoded video sequence, segmentation information describing how each macroblock of the image of the encoded video sequence is segmented, a mode indicating how each segment is encoded, one or more reference frames (and a list of reference frames) for each inter-frame codec block, and other information for decoding the encoded video sequence.

[0318] Intra-prediction unit 4503 can use, for example, an intra-prediction mode received in the bitstream to form prediction blocks from spatially adjacent blocks. Inverse quantization unit 4504 performs inverse quantization (i.e., dequantization) on the quantized video block coefficients provided in the bitstream and decoded by entropy decoding unit 4501. Inverse transform unit 4505 applies the inverse transform.

[0319] The reconstruction unit 4506 can add the residual block to the corresponding predicted block generated by the motion compensation unit 4502 or the intra-frame prediction unit 4503 to form a decoded block. If necessary, a deblocking filter can also be used to filter the decoded block to remove block artifacts. The decoded video block is then stored in a buffer 4507, which provides a reference block for subsequent motion compensation / intra-frame prediction and also generates decoded video for presentation on a display device.

[0320] Figure 7 This is a schematic diagram of an example encoder 4600. Encoder 4600 is suitable for implementing VVC techniques. Encoder 4600 includes three loop filters: a deblocking filter (DF) 4602, a sample adaptive compensation (SAO) 4604, and an adaptive loop filter (ALF) 4606. Unlike DF 4602, which uses predefined filters, SAO 4604 and ALF 4606 utilize the original samples of the current image, respectively, by adding an offset and by applying a finite impulse response (FIR) filter, and by utilizing the encoded / decoded side information through signal transmission offset and filter coefficients to reduce the mean square error between the original and reconstructed samples. ALF 4606 is located in the last processing stage of each image and can be considered as a tool to attempt to capture and repair artifacts caused by previous stages.

[0321] The encoder 4600 also includes an intra-frame prediction component 4608 and a motion estimation / compensation (ME / MC) component 4610 configured to receive input video. The intra-frame prediction component 4608 is configured to perform intra-frame prediction, while the ME / MC component 4610 is configured to perform inter-frame prediction using reference images obtained from a reference image buffer 4612. Residual blocks from inter-frame or intra-frame prediction are fed into a transform (T) component 4614 and a quantization (Q) component 4616 to generate quantized residual transform coefficients, which are then fed into an entropy coding component 4618. The entropy coding component 4618 entropy-codes the prediction results and the quantized transform coefficients and transmits them to a video decoder (not shown). The quantized components output from the quantization component 4616 can be fed into an inverse quantization (IQ) component 4620, an inverse transform component 4622, and a reconstruction (REC) component 4624. REC component 4624 is able to output images to DF 4602, SAO 4604 and ALF 4606 for filtering before these images are stored in reference image buffer 4612.

[0322] Figure 8 This is a flowchart of an example method 4700 for video processing. Method 4700 includes: in step 4702, determining dynamic metadata rendering information to be transmitted via signaling in a JPEG AI bitstream, wherein the dynamic metadata rendering information is transmitted via signaling in a syntax structure including: an indication of the dynamic metadata type, an indication of the size of the dynamic metadata, and data bytes of the dynamic metadata; and in step 4704, performing a conversion between visual media data and the JPEG AI bitstream based on the dynamic metadata rendering information. The conversion may include encoding at an encoder, decoding at a decoder, or a combination thereof.

[0323] It should be noted that method 4700 can be implemented in an apparatus for processing video data, including a processor and a non-transitory memory having instructions thereon, such as a video encoder 4400, a video decoder 4500, and / or an encoder 4600. In this case, the instructions, when executed by the processor, cause the processor to perform method 4700. Furthermore, method 4700 can be executed by a non-transitory computer-readable medium including a computer program product for use by a video encoding / decoding device. The computer program product includes computer-executable instructions stored on the non-transitory computer-readable medium, causing the video encoding / decoding device to perform method 4700 when executed by a processor.

[0324] The following provides a list of preferred solutions as examples.

[0325] The following solutions illustrate examples of the techniques discussed in this article.

[0326] 1. A method for processing media data, comprising: determining one or more of the following: code point (CICP) rendering information independent of encoding / decoding, mastering display color volume information, content brightness level information, and dynamic metadata, in a rendering information syntax structure included in the image header of a Joint Group of Image Experts (JPEG) Artificial Intelligence (AI) bitstream; and performing a conversion between visual media data and the JPEG AI bitstream based on the rendering information syntax structure.

[0327] 2. The method according to Solution 1, wherein the rendering information header tag syntax element is not transmitted via signal in the rendering information syntax structure.

[0328] 3. The method according to solution 1 or 2, wherein the JPEG AI stream transmits a portion, but not all, of the CICP rendering information, master production display color volume information, content brightness level information, and dynamic metadata via signal transmission.

[0329] 4. The method according to any one of solutions 1-3, wherein, for a specific type of rendering information, an indication is included in the JPEG AI stream to indicate the presence of that specific type of rendering information.

[0330] 5. The method according to any one of solutions 1-4, wherein, for each type of rendering information, an indication is included in the JPEG AI bitstream to indicate whether the corresponding type of rendering information exists.

[0331] 6. The method according to any one of solutions 1-5, wherein the syntax structure of the CICP rendering information comprises an integer number of bytes.

[0332] 7. The method according to any one of solutions 1-6, wherein a 7-bit syntax element, named cicp_reserved_zero_7bits, is included in the syntax structure of CICP rendering information, immediately following the image_full_range_flag syntax element.

[0333] 8. The method according to any one of solutions 1-7, wherein a 7-bit syntax element, named cicp_reserved_zero_7bits, is included in the syntax structure of CICP rendering information, immediately preceding the image_full_range_flag syntax element.

[0334] 9. The method according to any one of solutions 1-8, wherein dynamic metadata rendering information is transmitted via a signal through a syntax structure in the JPEGAI bitstream, the syntax structure including, in sequence, an indication of the dynamic metadata type, an indication of the size of the dynamic metadata, and data bytes of the dynamic metadata.

[0335] 10. The method according to any one of solutions 1-9, wherein the dynamic metadata type is indicated by an 8-bit syntax element named dm_type.

[0336] 11. The method according to any one of solutions 1-10, wherein dm_type equals a specific value of 0, indicating that the dynamic metadata is an ST2094-10_data() structure.

[0337] 12. The method according to any one of solutions 1-11, wherein some values ​​of dm_type are preserved.

[0338] 13. The method according to any one of solutions 1-12, wherein for a standard-compliant JPEG AI bitstream, the value of dm_type must be equal to 0.

[0339] 14. The method according to any one of solutions 1-13, wherein when encountering a dm_type greater than 0, the standard-compliant decoder must ignore the dynamic_metadata() syntax structure.

[0340] 15. The method according to any one of solutions 1-14, wherein the dynamic metadata is indicated by 16-bit syntax elements.

[0341] 16. The method according to any one of solutions 1-15, wherein the size of the dynamic metadata is indicated by an 8-bit syntax element.

[0342] 17. The method according to any one of solutions 1-16, wherein the length of the syntax element indicating the size of the dynamic metadata is indicated by another 1-bit or 2-bit syntax element.

[0343] 18. The method according to any one of solutions 1-17, wherein the conversion includes encoding visual media data into a JPEG AI stream.

[0344] 19. The method according to any one of solutions 1-17, wherein the conversion includes decoding visual media data from a JPEG AI bitstream.

[0345] 20. An apparatus for processing video data, comprising a processor and a non-transitory memory having instructions thereon, wherein the instructions, when executed by the processor, cause the processor to perform the method of any one of solutions 1-19.

[0346] 21. A non-transitory computer-readable medium comprising a computer program product for use by a video codec apparatus, the computer program product including computer-executable instructions stored on the non-transitory computer-readable medium, such that when the computer-executable instructions are executed by a processor, the video codec apparatus performs the method of any one of solutions 1-19.

[0347] 22. A non-transitory computer-readable recording medium storing a Joint Picture Experts Group (JPEG) Artificial Intelligence (AI) bitstream of video generated by a method performed by a video processing apparatus, wherein the method includes: determining one or more of the following: code point (CICP) rendering information independent of encoding / decoding, mastering display color volume information, content brightness level information, and dynamic metadata included in a rendering information syntax structure in the picture header of the JPEG AI bitstream; and generating the JPEG AI bitstream based on the determination.

[0348] 23. A method for storing a bitstream of video, comprising: determining that one or more of the following are included in a rendering information syntax structure in the image header of a Joint Picture Experts Group (JPEG) Artificial Intelligence (AI) bitstream: code point (CICP) rendering information independent of encoding / decoding, mastering display color volume information, content brightness level information, and dynamic metadata; generating a JPEG AI bitstream based on the determination; and storing the JPEG AI bitstream in a non-transitory computer-readable recording medium.

[0349] 24. A method, apparatus, or system described in this document.

[0350] The following solutions illustrate further examples of the techniques discussed in this article.

[0351] 1. A method for processing media data, comprising: determining dynamic metadata rendering information transmitted via signaling in a Joint Photo Experts Group (JPEG) Artificial Intelligence (AI) bitstream, wherein the dynamic metadata rendering information is transmitted via signaling in a syntactic structure comprising: an indication of a dynamic metadata type, an indication of a dynamic metadata size, and data bytes of the dynamic metadata; and performing a conversion between visual media data and a JPEG AI bitstream based on the dynamic metadata rendering information.

[0352] 2. The method according to Solution 1, wherein the dynamic metadata rendering information is transmitted via signals in the following order: an indication of the dynamic metadata type, followed by an indication of the size of the dynamic metadata, and then the data bytes of the dynamic metadata.

[0353] 3. The method described according to solution 1 or 2, wherein the dynamic metadata type (dm_type) is indicated by an 8-bit syntax element.

[0354] 4. The method according to any one of solutions 1-3, wherein dm_type equal to 0 specifies that the dynamic metadata is a European Telecommunications Standards Institute (ETSI) ST2094-10_data() structure.

[0355] 5. The method according to any one of solutions 1-4, wherein some values ​​of dm_type are preserved.

[0356] 6. The method according to any one of solutions 1-5, wherein for a standard-compliant JPEG AI bitstream, the value of dm_type must be equal to 0.

[0357] 7. The method according to any one of solutions 1-6, wherein when encountering a dynamic_metadata() syntax structure containing a dm_type with a value greater than 0, the standard-compliant decoder must ignore the dynamic_metadata() syntax structure.

[0358] 8. The method according to any one of solutions 1-7, wherein the size of the dynamic metadata is indicated by a 16-bit syntax element.

[0359] 9. The method according to any one of solutions 1-7, wherein the size of the dynamic metadata is indicated by an 8-bit syntax element.

[0360] 10. The method according to any one of solutions 1-9, wherein the length of the syntax element indicating the size of the dynamic metadata is indicated by another syntax element.

[0361] 11. The method according to any one of solutions 1-10, wherein the other syntax element is a 1-bit syntax element.

[0362] 12. The method according to any one of solutions 1-10, wherein the other syntax element is a 2-bit syntax element.

[0363] 13. The method according to any one of solutions 1-12, wherein the indicator of the size of the dynamic metadata (dm_size) is a sixteen-bit unsigned syntax element.

[0364] 14. The method according to any one of solutions 1-13, wherein the data byte (dm_data_byte[i]) of the dynamic metadata is an eight-bit bit string.

[0365] 15. The method according to any one of solutions 1-14, wherein the conversion includes encoding visual media data into a JPEG AI stream.

[0366] 16. The method according to any one of solutions 1-14, wherein the conversion includes decoding visual media data from a JPEG AI bitstream.

[0367] 17. An apparatus for processing video data, comprising a processor and a non-transitory memory having instructions thereon, wherein the instructions, when executed by the processor, cause the processor to perform the method of any one of solutions 1-16.

[0368] 18. A non-transitory computer-readable medium comprising a computer program product for use by a video codec apparatus, the computer program product including computer-executable instructions stored on the non-transitory computer-readable medium, such that when the computer-executable instructions are executed by a processor, the video codec apparatus performs the method of any one of solutions 1-16.

[0369] 19. A non-transitory computer-readable recording medium storing a Joint Photo Experts Group (JPEG) Artificial Intelligence (AI) bitstream of video generated by a method performed by a video processing apparatus, wherein the method includes: determining dynamic metadata rendering information transmitted via signaling in the Joint Photo Experts Group (JPEG) Artificial Intelligence (AI) bitstream, wherein the dynamic metadata rendering information is transmitted via signaling in a syntax structure including: an indication of dynamic metadata type, an indication of dynamic metadata size, and data bytes of dynamic metadata; and generating a JPEG AI bitstream based on the determination.

[0370] 20. A method for storing a bitstream of video, comprising: determining dynamic metadata rendering information in a Joint Picture Experts Group (JPEG) Artificial Intelligence (AI) bitstream via signaling, wherein the dynamic metadata rendering information is signaled in a syntax structure comprising: an indication of a dynamic metadata type, an indication of a dynamic metadata size, and data bytes of the dynamic metadata; generating a JPEG AI bitstream based on the determination; and storing the JPEG AI bitstream in a non-transitory computer-readable recording medium.

[0371] In the described solution, the encoder conforms to the format rules by generating an encoded representation based on those rules. In the described solution, the decoder parses the syntax elements in the encoded representation using known information about their presence or absence, according to the format rules, to produce the decoded video.

[0372] In this document, the term "video processing" can refer to video encoding, video decoding, video compression, or video decompression. For example, a video compression algorithm can be applied during the conversion from the pixel representation of a video to the corresponding bitstream representation, and vice versa. For example, the bitstream representation of the current video block can correspond to bits at the same position in the bitstream defined by the syntax or bits propagated at different positions. For example, a macroblock can be encoded based on the error residual value after transformation and encoding / decoding, and can also use bits from the header and other fields in the bitstream. Furthermore, during the conversion, the decoder can parse the bitstream based on this determination, knowing whether some fields may or may not be present, as described in the solutions above. Similarly, the encoder can determine whether to include or exclude specific syntax fields and generate encoded / decoded representations accordingly by including or excluding syntax fields from the encoded / decoded representation.

[0373] The disclosed and other solutions, examples, embodiments, modules, and functional operations described in this document can be implemented in digital electronic circuits, or in computer software, firmware, or hardware, including the structures disclosed in this document and their structural equivalents, or in one or more combinations thereof. The disclosed embodiments and other embodiments can be implemented as one or more computer program products, i.e., one or more computer program instruction modules encoded on a computer-readable medium for execution by or control of the operation of a data processing apparatus. The computer-readable medium can be a machine-readable storage device, a machine-readable storage substrate, a storage device, a material composition affecting machine-readable propagation signals, or a combination thereof. The term "data processing apparatus" encompasses all means, devices, and machines for processing data, including, for example, a programmable processor, a computer, or multiple processors or computers. In addition to hardware, the apparatus may also include, for example, code that creates an execution environment for a related computer program, such as code constituting processor firmware, a protocol stack, a database management system, an operating system, or a combination thereof. Propagation signals are artificially generated signals, such as machine-generated electrical signals, optical signals, or electromagnetic signals, which are generated to encode information to be transmitted to a suitable receiver device.

[0374] Computer programs (also known as programs, software, software applications, scripts, or code) can be written in any programming language, including compiled or interpreted languages, and can be deployed in any form, including standalone programs or modules, components, subroutines, or other units 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 related program, or in multiple co-located files (e.g., a file storing one or more modules, subroutines, or code portions). A computer program can be deployed to execute on one computer or on multiple computers located at a single site or distributed across multiple sites and interconnected by a communications network.

[0375] The processing and logic flows described in this document can be executed by one or more programmable processors that execute one or more computer programs to perform functions by manipulating input data and generating outputs. The processing and logic flows can also be executed by special-purpose logic circuitry, and the devices can be implemented as special-purpose logic circuitry, such as FPGAs (Field-Programmable Gate Arrays) or ASICs (Application-Specific Integrated Circuits).

[0376] Processors suitable for executing computer programs include, for example, general-purpose and special-purpose microprocessors, and any one or more processors in any type of digital computer. Typically, the processor receives instructions and data from read-only memory or random access memory, or both. The basic components of a computer are a processor that executes instructions and one or more storage devices that store the instructions and data. Typically, a computer will also include one or more mass storage devices for storing data, such as magnetic disks, magneto-optical disks, or optical disks. However, a computer does not necessarily have such devices. Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and storage devices, including, for example, semiconductor storage devices such as EPROM, EEPROM, and flash memory devices; magnetic disks, such as internal hard disks or removable hard disks; magneto-optical disks; and CD-ROMs and DVD-ROMs. The processor and memory may be supplemented by or incorporated into special-purpose logic circuitry.

[0377] While this patent document contains numerous details, these details should not be construed as limiting any subject matter or the scope of the claims, but rather as descriptions of features specific to particular embodiments of a particular technology. In this patent document, certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented separately in multiple embodiments, or in any suitable sub-combination. Furthermore, although features may function in certain combinations as described above, and even were originally claimed in this manner, in some cases one or more features in the claimed combination may be removed from that combination, and the claimed combination may be for sub-combinations or variations thereof.

[0378] Similarly, although operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring such operations to be performed sequentially in the specific order or sequence shown, or requiring all shown operations to be performed in order to achieve the desired result. Furthermore, the division of various system components in the embodiments described in this patent document should not be construed as requiring such division in all embodiments.

[0379] Only a few implementations and examples are described, and other implementations, improvements and variations can be made based on what is described and shown in this patent document.

[0380] When there are no intermediate components other than a line, trace, or other medium between the first and second components, the first component is directly coupled to the second component. When there are intermediate components other than a line, trace, or other medium between the first and second components, the first component is indirectly coupled to the second component. The term "coupled" and its variations include direct coupling and indirect coupling. The use of the term "about" means including a range of ±10% of the following figures, unless otherwise specified.

[0381] While several embodiments have been provided in this disclosure, it should be understood that the disclosed systems and methods may be embodied in many other specific forms without departing from the spirit or scope of this disclosure. The present examples are intended to be illustrative rather than limiting and are not intended to be limited to the details given herein. For example, various elements or components may be combined or integrated into another system, or certain features may be omitted or not implemented.

[0382] Furthermore, the 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 this disclosure. Other items shown or discussed as couplings may be directly connected or indirectly coupled or communicated through some interface, device, or intermediate component, whether electrical, mechanical, or otherwise. Other examples of variations, substitutions, and alterations will be apparent to those skilled in the art and may be made without departing from the spirit and scope of this disclosure.

Claims

1. A method for processing media data, comprising: It was determined that dynamic metadata rendering information is transmitted via signaling in the Joint Photographic Experts Group (JPEG) Artificial Intelligence (AI) bitstream, wherein the dynamic metadata rendering information is transmitted via signaling in a syntax structure including: an indication of the dynamic metadata type, an indication of the size of the dynamic metadata, and the data bytes of the dynamic metadata; and The conversion between visual media data and the JPEG AI stream is performed based on the dynamic metadata rendering information.

2. The method as described in claim 1, wherein, The dynamic metadata rendering information is transmitted via signals in the following order: the indication of the dynamic metadata type, then the indication of the size of the dynamic metadata, and then the data bytes of the dynamic metadata.

3. The method as described in claim 1 or 2, wherein, The dynamic metadata type (dm_type) is indicated by an 8-bit syntax element.

4. The method according to any one of claims 1-3, wherein, The fact that dm_type is equal to 0 indicates that the dynamic metadata is the European Telecommunications Standards Institute (ETSI) ST2094-10_data() structure.

5. The method according to any one of claims 1-4, wherein, Some values ​​of dm_type are preserved.

6. The method according to any one of claims 1-5, wherein, For standard JPEG AI streams, the value of dm_type must be equal to 0.

7. The method according to any one of claims 1-6, wherein, When encountering a dynamic_metadata() syntax structure containing a dm_type value greater than 0, a standard-compliant decoder must ignore the dynamic_metadata() syntax structure.

8. The method according to any one of claims 1-7, wherein, The size of the dynamic metadata is indicated by a 16-bit syntax element.

9. The method according to any one of claims 1-7, wherein, The size of the dynamic metadata is indicated by an 8-bit syntax element.

10. The method according to any one of claims 1-9, wherein, The length of the syntax element that indicates the size of the dynamic metadata is indicated by another syntax element.

11. The method according to any one of claims 1-10, wherein, The other syntax element is a 1-bit syntax element.

12. The method according to any one of claims 1-10, wherein, The other syntax element is a 2-bit syntax element.

13. The method according to any one of claims 1-12, wherein, The indication (dm_size) of the size of the dynamic metadata is a sixteen-bit unsigned syntax element.

14. The method according to any one of claims 1-13, wherein, The data byte (dm_data_byte[i]) of the dynamic metadata is an 8-bit bit string.

15. The method according to any one of claims 1-14, wherein, The conversion includes encoding the visual media data into the JPEG AI stream.

16. The method according to any one of claims 1-14, wherein, The conversion includes decoding the visual media data from the JPEG AI bitstream.

17. An apparatus for processing video data, comprising a processor and a non-transitory memory having instructions thereon, wherein, When executed by the processor, the instructions cause the processor to perform the method of any one of claims 1-16.

18. A non-transitory computer-readable medium comprising a computer program product for use with a video encoding / decoding device, wherein, The computer program product includes computer-executable instructions stored on the non-transitory computer-readable medium, such that when the computer-executable instructions are executed by a processor, the video codec device performs the method of any one of claims 1-16.

19. A non-transitory computer-readable recording medium storing a Joint Photo Experts Group (JPEG) artificial intelligence (AI) bitstream of video generated by a method performed by a video processing apparatus, wherein, The method includes: It was determined that dynamic metadata rendering information is transmitted via signaling in the Joint Photographic Experts Group (JPEG) Artificial Intelligence (AI) bitstream, wherein the dynamic metadata rendering information is transmitted via signaling in a syntax structure including: an indication of the dynamic metadata type, an indication of the size of the dynamic metadata, and the data bytes of the dynamic metadata; and The JPEG AI stream is generated based on the determination.

20. A method for storing a video bitstream, comprising: It is determined that dynamic metadata rendering information is transmitted via signaling in the Joint Image Experts Group (JPEG) Artificial Intelligence (AI) bitstream, wherein the dynamic metadata rendering information is transmitted via signaling in a syntax structure including: an indication of the dynamic metadata type, an indication of the size of the dynamic metadata, and the data bytes of the dynamic metadata; Based on the determination, the JPEG AI bitstream is generated; and The JPEG AI stream is stored in a non-transitory computer-readable recording medium.

Images