Digital Human Video Encoding, Decoding and Transmission
By combining the generation of facial video SEI messages with a generative network, the problem of high bandwidth consumption in digital video is solved, enabling efficient digital human video encoding, decoding, and transmission.
Patent Information
- Application Number
- CN202580028625.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2024-04-17
- Filing Date
- 2025-04-17
- Publication Date
- 2026-11-17
AI Technical Summary
Digital video consumes the largest bandwidth on the Internet and other digital communication networks. As the number of connected user devices increases, bandwidth demand continues to grow, and existing technologies struggle to efficiently encode, decode, and transmit digital human videos.
By employing Generative Face Video (GFV) supplemental enhancement information (SEI) messages, digital human videos are generated and transmitted using multiple basic images during the encoding and decoding process through a generative network. Facial feature data is processed and fused using a generative neural network.
It improves video encoding and decoding efficiency, reduces bandwidth requirements, and enables efficient digital human video transmission and display.
Smart Images

Figure CN123125879A_ABST
Abstract
Description
[0001] Cross-references to related applications
[0002] This application claims priority and rights to International Patent Application No. PCT / CN2024 / 088203, filed on April 17, 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 consumes the largest amount 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 multiple base images to be used in a generative model including a generative network for digital human videos, the generative network employing Generative Face Video (GFV) Supplemental Enhancement Information (SEI) messages to encode and decode video information; and performing a conversion between visual media data and a bitstream based on the GFV SEI messages.
[0006] The second aspect relates to 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 any of the aspects described above.
[0007] The third aspect relates to a non-transitory computer-readable medium including 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 executed by a processor, the video codec apparatus performs the methods of any of the preceding aspects.
[0008] The fourth aspect relates to a non-transitory computer-readable recording medium storing a bitstream of video generated by a method performed by a video processing apparatus, wherein the method includes: determining multiple basic images to be used in a generative model including a generative network for digital human video, the generative network employing Generative Face Video (GFV) Supplemental Enhancement Information (SEI) messages to encode and decode video information; and based on the determined generated bitstream.
[0009] The fifth aspect relates to a method for storing a bitstream of video, comprising: determining multiple base images to be used in a generative model including a generative network for digital human video, the generative network employing Generative Face Video (GFV) Supplemental Enhancement Information (SEI) messages to encode and decode video information; based on the determined generative bitstream; and storing the 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 foregoing embodiments to create new embodiments within the scope of this disclosure.
[0011] These and other features will be more clearly understood through the following detailed description 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 A facial video compression scheme is shown.
[0014] Figure 2 This is a block diagram illustrating an example video processing system.
[0015] Figure 3 This is a block diagram of an example video processing device.
[0016] Figure 4 This is a flowchart of an example method for video processing.
[0017] Figure 5 This is a block diagram illustrating an example video codec system.
[0018] Figure 6 This is a block diagram showing an example encoder.
[0019] Figure 7 This is a block diagram showing an example decoder.
[0020] Figure 8 This is a schematic diagram of an example encoder.
[0021] Figure 9 This is a flowchart of an example method for video processing. Detailed Implementation
[0022] 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 shown below, including the exemplary designs and implementations shown and described herein, but modifications can be made within the scope of the appended claims and all their equivalents.
[0023] 1. Preliminary Discussion
[0024] This document relates to encoding / decoding and transmission technologies. Specifically, this disclosure relates to generating digital human videos using key image / video segments and metadata. These ideas can be applied individually or in various combinations to image / video bitstreams encoded and decoded by any codec, such as the Multi-Functional Video Codec (VVC) standard and / or the Multi-Functional SEI Message (VSEI) standard for encoding and decoding video bitstreams.
[0025] 2. Abbreviation
[0026] This paper uses the following abbreviations: Adaptation Parameter Set (APS), Access Unit (AU), Coded Layer Video Sequence (CLVS), Coded Layer Video Sequence Start (CLVSS), Cyclic Redundancy Check (CRC), Coded Video Sequence (CVS), Finite Impulse Response (FIR), Intra Random Access Point (IRAP), Network Abstraction Layer (NAL), Neural-Network Post-Processing Filter (NNPF), Neural-Network Post-Filter Activation (NNPFA), Neural-Network Post-Filter Characteristics (NNPFC), Picture Parameter Set (PPS), Picture Unit (PU), Random Access Skipped Leading. RASL), Supplemental Enhancement Information (SEI), Step-wise Temporal Sublayer Access (STSA), Uniform Resource Identifier (URI), Video Coding Layer (VCL), Multifunctional Supplemental Enhancement Information (Recommendation ITU-T H.274 | ISO / IEC 23002-7) (VSEI), Video Usability Information (VUI), Multifunctional Video Coding (Recommendation ITU-T H.266 | ISO / IEC 23090-3) (VVC)
[0027] 3. Further discussion
[0028] 3.1 Digital Human Video
[0029] Digital Human Video is a type of generated video that includes some visual samples of one or more humans and features that match the video.
[0030] 3.2 Video Coding and Decoding Standards
[0031] Video coding standards have evolved primarily through the development of standards by the International Telecommunication Union Telecommunication Standardization Sector (ITU-T) and the International Organization for Standardization (ISO) / International Electrotechnical Commission (IEC). ITU-T developed the H.261 and H.263 standards, while ISO / IEC developed the MPEG-1 and MPEG-4 visual standards led by the Moving Picture Experts Group (MPEG). The two organizations jointly developed the H.262 / MPEG-2 video standard, the H.264 / MPEG-4 Advanced Video Coding (AVC) standard, and the H.265 / High Efficiency Video Coding (HEVC) standard.[1] Starting with H.262, video coding standards are based on a hybrid video coding architecture that utilizes temporal prediction plus transform coding. In order to explore future video coding technologies beyond HEVC, the Joint Video Exploration Team (JVET) was established by the Video Coding Experts Group (VCEG) and MPEG. JVET adopted many methods and incorporated them into a reference software called the Joint Exploration Model (JEM).[2] When the Multi-Functional Video Codec (VVC) project was officially launched, the Joint Video Exploration Team (JVET) was later renamed the Joint Video Experts Team (JVET). VVC[3] is a codec standard managed by JVET, with the goal of reducing the bit rate by 50% compared to HEVC.
[0032] The Multi-Functional Video Coding (VVC) standard (ITU-T H.266 | ISO / IEC 23090-3) [3] and the related Multi-Functional Supplemental Enhancement Information (VSEI) standard (ITU-T H.274 | ISO / IEC 23002-7) [4] are designed for the widest range of applications, including simple uses such as television broadcasting, video conferencing or playback from storage media, as well as more advanced use cases such as adaptive bitrate streaming, video region extraction, synthesis and merging of content from multiple codec video bitstreams, multi-view video, scalable layered coding and decoding and viewport adaptive 360° immersive media.
[0033] The Basic Video Codec (EVC) standard (ISO / IEC 23094-1) is another video codec standard developed by MPEG.
[0034] 3.3 SEI Messages in General Cases and in VVC and VSEI
[0035] Supplemental Enhancement Information (SEI) messages assist in processes related to decoding, display, or other purposes. However, SEI messages are not essential for constructing luma or chroma samples during the decoding process. Standard-compliant decoders do not need to process this information to achieve output order consistency. Some SEI messages are necessary for checking bitstream consistency and output timing decoder consistency. Other SEI messages are not necessary for bitstream consistency checks.
[0036] Appendix D of VVC specifies the syntax and semantics of the SEI message payload for some SEI messages, and specifies the use of SEI messages and VUI parameters whose syntax and semantics are specified in ITU-TH.274 | ISO / IEC 23002-7.
[0037] 3.4 Generate facial video SEI message
[0038] Figure 1 A facial video compression scheme 100 is illustrated. This scheme was proposed to JVET. In this scheme, some base images (also called key images) are encoded and decoded using a video codec (e.g., VVC), and subsequent images include metadata of facial features (e.g., head position, eye matrices representing the opening and closing state and level of the eyes). The decoder uses a generative neural network to form a decoded video based on these key images and subsequent facial feature data.
[0039] JVET-AG2032[6] includes a specification for generating facial video SEI messages, as shown below.
[0040] 8.37.1 Syntax for Generating Face Video SEI Messages
[0041]
[0042]
[0043]
[0044]
[0045] 8.37.1 Generating Facial Video SEI Message Semantics
[0046] The Generative Face Video (GFV) SEI message indicates facial parameters and specifies a face parameter converter neural network (denoted as TranslatorNN()) and a face image generator neural network (denoted as GenerativeNN()). The TranslatorNN() can be used to convert facial parameters of various formats transmitted via signals in the SEI message into parameters of a fixed format. The GenerativeNN() can be used to generate an output image using the fixed format facial parameters and the previously decoded output image.
[0047] Note 1 – Facial parameters can be determined from the source image before encoding. Such a source image can be called a driving image.
[0048] Note 2 – The previously decoded output image input to GenerativeNN() can be a base image (providing a decoded output image with a reference texture, upon which the face image can be generated), and optionally, it can be an image that can be fused by GenerativeNN() to improve background texture and facial details. When the current image is not a base image, GFV SEI messages can be used to generate a face image based on the previously decoded base image, the facial parameters conveyed by the GFV SEI message, and optionally the currently decoded image, for the purpose of fusion.
[0049] To use this SEI message, the following variables need to be defined:
[0050] - Enter the width and height of the image, in units of brightness samples, which are represented here as CroppedWidth and CroppedHeight, respectively.
[0051] - The luminance sample array baseCroppedYPic, chrominance sample array baseCroppedCbPic, and baseCroppedCrPic corresponding to the decoded output image (represented as BasePicture) of the source base image.
[0052] - The luminance sample array driveCroppedYPic, the chrominance sample array driveCroppedCbPic, and the chrominance sample array driveCroppedCrPic corresponding to the decoded output image (represented as DrivePicture) of the source driving image.
[0053] - BitDepth of the brightness sample array of the input image Y .
[0054] - Bit depth of the chroma sample array (if any) of the input image. C .
[0055] - Chroma format indicator, denoted here as ChromaFormatIdc, as described in sub-entry 7.3.
[0056] The variables SubWidthC and SubHeightC are derived from ChromaFormatIdc, as specified in Table 2.
[0057] The `gfv_id` contains an identifier that can be used to identify facial feature information and specify the neural network that can be used as a TranslatorNN(). The value of `gfv_id` must be in the range of 0 to 2^32–2 (inclusive). Values of `gfv_id` from 256 to 511 (inclusive) and from 2^31 to 2^32–2 (inclusive) are reserved for future use by ITU-T | ISO / IEC. Decoders conforming to this version of this document must ignore GFV SEI messages when they encounter a `gfv_id` in the range of 256 to 511 (inclusive) or 2^31 to 2^32–2 (inclusive).
[0058] Note 3 – For example, when there is more than one face in the output image, different values of gfv_id in different GFV SEI messages can be used to identify different faces.
[0059] gfv_cnt specifies the GFV SEI message instance count value for the gfv_id value within the image unit.
[0060] The first GFV SEI message (in decoding order) with a specific value of gfv_id within a picture unit must have gfv_cnt equal to 0. When gfv_cnt assigned to currGfvCnt is greater than 0, within the same picture unit, GFV SEI messages with the same gfv_id value and gfv_cnt equal to currGfvCnt - 1 must precede the current GFV SEI message in decoding order.
[0061] The value of gfv_cnt must be in the range of 0 to 65,535 (inclusive).
[0062] A value of 1 for `gfv_base_pic_flag` indicates that the currently decoded output image corresponds to a base image. A value of 0 for `gfv_base_pic_flag` indicates that the currently decoded output image does not correspond to a base image, or that the SEI message does not specify the syntax elements of a base image. When `gfv_cnt` is greater than 0, `gfv_base_pic_flag` must be equal to 0.
[0063] The following constraints apply to the value of gfv_base_pic_flag:
[0064] – When the GFV SEI message is the first GFV SEI message with a specific gfv_id value in the current CLVS (in the order of decoding), the value of gfv_base_pic_flag must be equal to 1.
[0065] – When the gfv_base_pic_flag of a GFV SEI message with a specific gfv_id value is equal to 0, the SEI message applies to the current decoded picture and all subsequent decoded pictures of the current layer (in output order), up to the earlier of the following: the end of the current CLVS, or the decoded picture (excluding the decoded picture) that is after the current decoded picture in output order within the current CLVS and is associated with a subsequent GFV SEI message (in decoding order) within the current CLVS, which has a gfv_base_pic_flag value equal to 0 and the specific gfv_id value.
[0066] A value of 1 for `gfv_nn_present_flag` indicates that the SEI message contains or indicates a neural network that can be used as a TranslatorNN(). A value of 0 for `gfv_nn_present_flag` indicates that the SEI message does not contain or indicate a neural network that can be used as a TranslatorNN(). When `gfv_nn_present_flag` does not exist, it is presumed to be 0.
[0067] When a GFV SEI message with a specific value of gfv_id exists in an IRAP picture unit or in a picture unit following the IRAP picture unit in output order, and no picture unit before that picture unit (in output order) has a GFV SEI message with that specific value of gfv_id that appears after the IRAP picture unit (in output order), gfv_nn_present_flag must exist and be equal to 1.
[0068] When gfv_nn_present_flag equals 0 and the TranslatorNN is referenced in the semantics of the SEI message, the applicable TranslatorNN is defined by the GFV SEI message present in the last preceding picture unit (in output order), which has the same gfv_id value and gfv_nn_present_flag equal to 1 as the current GFV SEI message.
[0069] `gfv_nn_base_flag`, `gfv_nn_mode_idc`, `gfv_nn_reserved_zero_bit_a`, `gfv_nn_tag_uri`, `gfv_nn_uri`, and `gfv_nn_payload_byte[i]` specify neural networks that can be used as TranslatorNN(). `gfv_nn_base_flag`, `gfv_nn_mode_idc`, `gfv_nn_reserved_zero_bit_a`, `gfv_nn_tag_uri`, `gfv_nn_uri`, and `gfv_nn_payload_byte[i]` have the same syntax and semantics as `nnpfc_base_flag`, `nnpfc_mode_idc`, `nnpfc_reserved_zero_bit_a`, `nnpfc_tag_uri`, `nnpfc_uri`, and `nnpfc_payload_byte[i]`, respectively.
[0070] GFV SEI messages must have the same SEI payload content if any of the following conditions are true:
[0071] – GFV SEI messages exist in the same image unit, have a gfv_cnt value equal to 0, have an existing gfv_nn_base_flag, and have the same gfv_id and gfv_nn_base_flag values.
[0072] – GFV SEI messages exist in the same image unit, have the same gfv_cnt value greater than 0, and have the same gfv_id value.
[0073] When `gfv_drive_pic_fusion_flag` exists, a value of 1 indicates that the currently decoded image can be input into `GenerativeNN()`, and this currently decoded image corresponds to the driving image that can be used for fusion. A value of 0 for `gfv_drive_pic_fusion_flag` indicates that the currently decoded image should not be input into `GenerativeNN()`.
[0074] Note 3 – For example, a value of 1 for gfv_drive_pic_fusion_flag can be used to indicate that the currently decoded image can be used to improve facial details or process background changes.
[0075] Note 4 – Fusion takes three inputs: a base image, features from keypoints and / or matrices carried in the GFV SEI message, and the currently decoded image, and outputs an image.
[0076] Note 5 – When the current decoded image corresponds to the driving image, it should be marked as not for output purposes.
[0077] A value of 1 for `gfv_coordinate_present_flag` indicates that the coordinate information of the key point exists. A value of 0 for `gfv_coordinate_present_flag` indicates that the coordinate information of the key point does not exist.
[0078] The requirement for bitstream consistency is that when gfv_matrix_type_idx[i] is equal to 0 or 1 (for any i from 0 to gfv_num_matrix_types_minus1), the value of gfv_coordinate_present_flag must be equal to 1.
[0079] Incrementing gfv_coordinate_precision_factor_minus1 by 1 indicates the length (in bits) of the syntax elements gfv_coordinate_x_abs[i], gfv_coordinate_y_abs[i], gfv_coordinate_z_abs[i], gfv_coordinate_dx_abs[i], gfv_coordinate_dy_abs[i], and gfv_coordinate_dz_abs[i].
[0080] Incrementing gfv_num_kps_minus1 by 1 indicates the number of keypoints. The value of gfv_num_kp_minus1 must be in the range of 0 to 2^10 – 1 (inclusive).
[0081] A value of 1 for gfv_kp_pred_flag indicates that the syntax elements gfv_coordinate_dx_abs[i], gfv_coordinate_dy_abs[i], and gfv_coordinate_dz_abs[i] exist, and that the syntax elements gfv_coordinate_dx_sign_flag[i], gfv_coordinate_dy_sign_flag[i], and gfv_coordinate_dz_sign_flag[i] may exist. A value of 0 for gfv_kp_pred_flag indicates that gfv_coordinate_x_abs[i], gfv_coordinate_y_abs[i], and gfv_coordinate_z_abs[i] exist, and that the syntax elements gfv_coordinate_x_sign_flag[i], gfv_coordinate_y_sign_flag[i], and gfv_coordinate_z_sign_flag[i] may exist.
[0082] A value of 1 for `gfv_coordinate_z_present_flag` indicates that the z-axis coordinate information of the key point exists. A value of 0 for `coordinate_z_present_flag` indicates that the z-axis coordinate information of the key point does not exist.
[0083] The increment of 1 in gfv_coordinate_z_max_value_minus1 indicates the maximum absolute value of the z-axis coordinate of the key point.
[0084] gfv_coordinate_x_abs[i] indicates the normalized absolute value of the x-axis coordinate of the i-th key point.
[0085] `gfv_coordinate_x_sign_flag[i]` specifies the sign of the x-axis coordinate of the i-th keypoint. When `gfv_coordinate_x_sign_flag[i]` does not exist, it is presumed to be equal to 0.
[0086] gfv_coordinate_y_abs[i] specifies the normalized absolute value of the y-axis coordinate of the i-th key point.
[0087] `gfv_coordinate_y_sign_flag[i]` specifies the sign of the y-axis coordinate of the i-th keypoint. When `gfv_coordinate_y_sign_flag[i]` does not exist, it is presumed to be equal to 0.
[0088] gfv_coordinate_z_abs[i] specifies the normalized absolute value of the z-axis coordinate of the i-th key point.
[0089] `gfv_coordinate_z_sign_flag[i]` specifies the sign of the z-axis coordinate of the i-th keypoint. When `gfv_coordinate_z_sign_flag[i]` does not exist, it is presumed to be equal to 0.
[0090] gfv_coordinate_dx_abs[i] indicates the absolute difference of the normalized values of the x-axis coordinates of the i-th keypoint.
[0091] `gfv_coordinate_dx_sign_flag[i]` specifies the sign of the difference in the x-axis coordinates of the i-th keypoint. When `gfv_coordinate_dx_sign_flag[i]` does not exist, it is presumed to be equal to 0.
[0092] gfv_coordinate_dy_abs[i] specifies the absolute difference of the normalized y-axis coordinates of the i-th key point.
[0093] `gfv_coordinate_dy_sign_flag[i]` specifies the sign of the difference in the y-axis coordinates of the i-th keypoint. When `gfv_coordinate_yd_sign_flag[i]` does not exist, it is presumed to be equal to 0.
[0094] gfv_coordinate_dz_abs[i] specifies the absolute difference of the normalized z-axis coordinates of the i-th key point.
[0095] `gfv_coordinate_dz_sign_flag[i]` specifies the sign of the difference in the z-axis coordinates of the i-th keypoint. When `gfv_coordinate_dz_sign_flag[i]` does not exist, it is presumed to be equal to 0.
[0096] The variables coordinateDeltaX[i], coordinateDeltaY[i], and coordinateDeltaZ[i] indicate the incremental x-axis coordinate, incremental y-axis coordinate, and incremental z-axis coordinate of the i-th key point, respectively. Their derivation is as follows:
[0097] coordinateDeltaX[i]=
[0098] coordinateDeltaY[i]=
[0099] coordinateDeltaZ[i]=
[0100] The variables coordinateX[i], coordinateY[i], and coordinateZ[i] indicate the x-axis coordinate, y-axis coordinate, and z-axis coordinate of the i-th key point, respectively. Their derivation is as follows:
[0101] When gfv_kp_pred_flag equals 0
[0102] coordinateX[i] =
[0103] coordinateY[i] =
[0104] coordinateZ[i]=
[0105] When gfv_kp_pred_flag equals 1
[0106] if( gfv_base_pic_flag ) {
[0107] coordinateX[ i ] = (( i > 0 ) ? coordinateX[ i - 1 ] : 0 ) +coordinateDeltaX[ i ]
[0108] coordinateY[ i ] = (( i > 0 ) ? coordinateY[ i - 1 ] : 0 ) +coordinateDeltaY[ i ]
[0109] coordinateZ[ i ] = (( i > 0 ) ? coordinateZ[ i - 1 ] : 0 ) +coordinateDeltaZ[ i ]
[0110] }
[0111] else {
[0112] coordinateX[ i ] = BaseKpCoordinateX[ i ] + coordinateDeltaX[ i ]
[0113] coordinateY[ i ] = BaseKpCoordinateY[ i ] + coordinateDeltaY[ i ]
[0114] coordinateZ[ i ] = BaseKpCoordinateZ[ i ] + coordinateDeltaZ[ i ]
[0115] }
[0116] Where BaseKpCoordinateX[i], BaseKpCoordinateY[i], and BaseKpCoordinateZ[i] indicate the x-axis, y-axis, and z-axis coordinates of the i-th keypoint in the base image, respectively, and their derivation is as follows:
[0117] if( gfv_base_pic_flag ) {
[0118] BaseKpCoordinateX[ i ] = coordinateX[ i ]
[0119] BaseKpCoordinateY[ i ] = coordinateY[ i ]
[0120] BaseKpCoordinateZ[ i ] = coordinateZ[ i ]
[0121] }
[0122] A value of 1 for `gfv_matrix_present_flag` indicates that the matrix parameter exists. A value of 0 for `gfv_matrix_present_flag` indicates that the matrix parameter does not exist.
[0123] The increment of gfv_matrix_element_precision_factor_minus1 indicates the length (in bits) of the syntax elements gfv_matrix_element_dec[i][j][k][m] and gfv_matrix_delta_element_dec[i][j][k][m].
[0124] Incrementing gfv_num_matrix_types_minus1 by 1 indicates the number of matrix types transmitted via signals in the SEI message. The value of gfv_matrix_type_num_minus1 must be in the range of 0 to 26 – 1 (inclusive).
[0125] A value of 1 for `gfv_matrix_pred_flag` indicates that the syntax elements `gfv_matrix_element_int[i][j][k][m]` and `gfv_matrix_element_dec[i][j][k][m]` exist, and `gfv_matrix_element_sign_flag[i][j][k][m]` can exist. A value of 0 for `gfv_matrix_pred_flag` indicates that `gfv_matrix_delta_element_int[i][j][k][m]` and `gfv_matrix_delta_element_dec[i][j][k][m]` exist, and `gfv_matrix_delta_element_sign_flag[i][j][k][m]` can exist. When `gfv_matrix_pred_flag` does not exist, it is presumed to be 0.
[0126] gfv_matrix_type_idx[i] indicates the index of the i-th matrix type, as specified in Table 3.
[0127] Table 3 – Specifications for gfv_matrix_type_idx
[0128]
[0129] Note 6. Undefined matrix types are used to represent matrix types other than affine translation matrices, covariance matrices, rotation matrices, translation matrices, and compact eigenma matrices. They can be used by the user to extend matrix types.
[0130] `gfv_num_matrices_equal_to_num_kps_flag[i]` equal to 1 indicates that the number of matrices of the i-th matrix type is equal to `gfv_num_kps_minus1 + 1`. `gfv_num_matrices_equal_to_num_kps_flag[i]` equal to 0 indicates that the number of matrices of the i-th matrix type is not equal to `gfv_num_coordinates_minus1 + 1`.
[0131] gfv_num_matrices_info[i] provides information for deriving the number of matrices of the i-th matrix type.
[0132] The increment of gfv_matrix_width_minus1[i] indicates the width of the matrix of the i-th matrix type.
[0133] The increment of gfv_matrix_height_minus1[i] indicates the height of the matrix of type i.
[0134] `gfv_matrix_for_3D_space_flag[i]` equal to 1 indicates that the matrix of type `i` is defined in three-dimensional space. `gfv_matrix_for_3D_space_flag[i]` equal to 0 indicates that the matrix of type `i` is defined in two-dimensional space.
[0135] When gfv_matrix_width_minus1[i] does not exist, it is presumed to be as follows:
[0136] –– If gfv_matrix_type_idx[i] is equal to 0, 1 or 4, and one of coordinate_z_present_flag and gfv_matrix_for_3D_space_flag[i] exists and is equal to 1, then gfv_matrix_width_minus1[i] is presumed to be equal to 2.
[0137] –– Otherwise, if matrix_type_idx[i] is equal to 0, 1 or 4, and one of coordinate_z_present_flag and gfv_matrix_for_3D_space_flag[i] exists and is equal to 0, then gfv_matrix_width_minus1[i] is presumed to be equal to 1.
[0138] Otherwise (matrix_type_idx[i] equals 5 or 6), gfv_matrix_width_minus1[i] is presumed to be equal to 0.
[0139] When gfv_matrix_height_minus1[i] does not exist, it is presumed to be as follows:
[0140] –– If matrix_type_idx is equal to 0, 1, 4, 5 or 6, and one of gfv_coordinate_z_present_flag and gfv_matrix_for_3D_space_flag[i] exists and is equal to 1, then gfv_matrix_height_minus1[i] is presumed to be equal to 2.
[0141] –– Otherwise (gfv_matrix_type_idx is equal to 0, 1, 4, 5 or 6, and one of gfv_coordinate_z_present_flag and gfv_matrix_for_3D_space_flag[i] is 0), gfv_matrix_height_minus1[i] is presumed to be equal to 1.
[0142] The variables matrixWidth[i] and matrixHeight[i] indicate the width and height of the matrix of type i, and their derivation is as follows:
[0143] matrixWidth[ i ] = gfv_matrix_width_minus1[ i ] + 1
[0144] matrixHeight[ i ] = gfv_matrix_height_minus1[ i ] + 1
[0145] The increment of gfv_num_matrices_minus1[i] indicates the number of matrices of the i-th matrix type.
[0146] The variable numMatrices[i] indicates the number of matrices of the i-th matrix type, and its derivation is as follows:
[0147] if( gfv_matrix_type_idx[ i ] == 0 || gfv_matrix_type_idx[ i ] == 1 ){
[0148] if(gfv_coordinate_present_flag)
[0149] numMatrices[ i ] = gfv_num_matrices_equal_to_num_kps_flag[ i ] ? gfv_num_kps_minus1 + 1 : ( gfv_num_matrices_info[ i ] < gfv_num_kp_minus1 ? gfv_num_matrices_info [ i ] + 1 : gfv_num_matrices_info [ i ] + 2 )
[0150] else
[0151] numMatrices[ i ] = gfv_num_matrices_info[ i ] + 1
[0152] }
[0153] else if( gfv_matrix_type_idx[ i ] >= 2 && gfv_matrix_type_idx[ i ] <7)
[0154] numMatrices[i] = 1
[0155] else
[0156] numMatrices[ i ] = gfv_num_matrices_minus1[ i ] + 1
[0157] gfv_matrix_element_int[i][j][k][m] indicates the integer part of the value of the matrix element at position (m, k) of the j-th matrix of the i-th matrix type.
[0158] gfv_matrix_element_dec[i][j][k][m] indicates the fractional part of the value of the matrix element at position (m, k) of the j-th matrix of the i-th matrix type.
[0159] `gfv_matrix_element_sign_flag[i][j][k][m]` indicates the sign of the matrix element at position (m, k) of the j-th matrix of the i-th matrix type. When `gfv_matrix_element_sign_flag[i][j][k][m]` does not exist, it is presumed to be equal to 0.
[0160] gfv_matrix_delta_element_int[i][j][k][m] indicates the integer part of the difference between the matrix elements at position (m, k) of the j-th matrix of the i-th matrix type.
[0161] gfv_matrix_delta_element_dec[i][j][k][m] indicates the fractional part of the difference between the matrix elements at position (m, k) of the j-th matrix of the i-th matrix type.
[0162] `gfv_matrix_delta_element_sign_flag[i][j][k][m]` indicates the sign of the difference between the matrix elements at position (m, k) of the j-th matrix of the i-th matrix type. When `gfv_matrix_element_sign_flag[i][j][k][m]` does not exist, it is presumed to be equal to 0.
[0163] The variable matrixElementDeltaVal[i][j][k][m] represents the difference between the matrix elements at position (m, k) of the j-th matrix of the i-th matrix type. Its derivation is as follows:
[0164] matrixElementDeltaVal[i][j][k][m]=
[0165]
[0166] The variable matrixElementVal[i][j][k][m] represents the value of the matrix element at position (m, k) of the j-th matrix of the i-th matrix type. Its derivation is as follows:
[0167] When gfv_matrix_pred_flag equals 0:
[0168] matrixElementVal[ i ][ j ][ k ][ m ] =
[0169] if( gfv_base_pic_flag )
[0170] BaseMatrixElementVal[ i ][ j ][ k ][ m ] = matrixElementVal[ i ][ j ][ k ][ m ]
[0171] When gfv_matrix_pred_flag equals 1:
[0172] matrixElementVal[ i ][ j ][ k ][ m ] = BaseMatrixElementVal[ i ][ j ][ k ][ m ] + matrixElementDeltaVal[ i ][ j ][ k ][ m ] +
[0173] For a given gfv_id value, the following process is performed in ascending order of gfv_cnt to generate a video image for each GFV SEI message, which has a gfv_base_pic_flag equal to 0 and a unique gfv_cnt value within the image unit:
[0174] DeriveSigParam()
[0175] TranslatorNN (sigKeyPoint, sigMatrix)
[0176] DeriveInputTensors()
[0177] if( gfv_base_pic_flag == 0 && gfv_drive_pic_fusion_flag == 0) {
[0178] if(ChromaFormatIdc == 0 )
[0179] GenerativeNN( inputBaseY, inputBaseKeyPoint, inputBaseMatrix, inputDriveKeyPoint, inputDriveMatrix)
[0180] else
[0181] GenerativeNN( inputBaseY, inputBaseCb, inputBaseCr, inputBaseKeyPoint, inputBaseMatrix, inputDriveKeyPoint, inputDriveMatrix)
[0182] }
[0183] else if(gfv_base_pic_flag == 0 && gfv_drive_pic_fusion_flag == 1) {
[0184] if(ChromaFormatIdc == 0 )
[0185] GenerativeNN( inputBaseY, inputDriveY, inputBaseKeyPoint, inputBaseMatrix, inputDriveKeyPoint, inputDriveMatrix)
[0186] else
[0187] GenerativeNN( inputBaseY, inputBaseCb, inputBaseCr,inputDriveY, inputDriveCb, inputDriveCr , inputBaseKeyPoint,inputBaseMatrix,, inputDriveKeyPoint, inputDriveMatrix)
[0188] }
[0189] StoreOutputTensors()
[0190] The procedure for deriving the input to TranslatorNN(), DeriveSigParam(), is defined as follows:
[0191] The keypoint coordinate array sigKeyPoint and the matrix sigMatrix are derived as follows:
[0192] if( gfv_coordinate_present_flag ) {
[0193] for ( i = 0; i< = gfv_num_kps_minus1; i++ ) {
[0194] sigKeyPoint[ i ][ 0 ] = coordinateX[ i ]
[0195] sigKeyPoint[ i ][ 1 ] = coordinateY[ i ]
[0196] if ( gfv_coordinate_z_present_flag )
[0197] sigKeyPoint[ i ][ 2 ] = coordinateZ[ i ]
[0198] }
[0199] }
[0200] else {
[0201] for ( i = 0; i < =num_kps_minus1; i++ ) {
[0202] sigKeyPoint [ i ][ 0 ] = 0
[0203] sigKeyPoint [ i ][ 1 ] = 0
[0204] if ( gfv_coordinate_z_present_flag )
[0205] sigKeyPoint [ i ][ 2 ] = 0
[0206] }
[0207] }
[0208] if( gfv_matrix_present_flag ) {
[0209] for ( i = 0; i <= gfv_num_matrix_types_minus1; i++ ) {
[0210] for ( j = 0; j < numMatrices[ i ]; j++ ) {
[0211] for( k = 0; k < matrixHeight [ i ]; k++ ) {
[0212] for ( l = 0; l < matrixWidth [ i ]; l++) {
[0213] sigMatrix[ i ][ j ][ k ][ l ] =matrixElementVal[ i ][ j][ k][ l ]
[0214] }
[0215] }
[0216] }
[0217] }
[0218] }
[0219] else {
[0220] for ( i = 0; i <= gfv_num_matrix_types_minus1; i++ ) {
[0221] for ( j = 0; j < numMatrices[ i ]; j++ ) {
[0222] for( k = 0; k < matrixHeight [ i ]; k++ ) {
[0223] for ( l = 0; l < matrixWidth [ i ]; l++) {
[0224] sigMatrix [i][j][k][l] = 0
[0225] }
[0226] }
[0227] }
[0228] }
[0229] }
[0230] TranslatorNN() is the process of converting facial parameters in various formats carried in SEI messages into fixed-format facial parameters, which are then input into the generator network to produce the output image.
[0231] The input to TranslatorNN() is:
[0232] - sigKeyPoint and sigMatrix
[0233] The output of TranslatorNN() is:
[0234] - convKeyPoint and convNumKeyPoint
[0235] - convMatrix and convNumMatrix, convMatrixWidth, convMatrixHeight
[0236] The procedure DeriveInputTensors() is used to derive the inputs of GenerativeNN(), and it is defined as follows:
[0237] When gfv_base_pic_flag equals 1, the basic image input tensors inputBaseY, inputBaseCb, and inputBaseCr are derived as follows:
[0238] for( x = 0; x < CroppedWidth; x++ ) {
[0239] for ( y = 0; y < CroppedHeight; y++ ) {
[0240] inputBaseY[ x ][ y ] = InpY( baseCroppedYPic[ x ][ y ])
[0241] }
[0242] }
[0243] if (ChromaFormatIdc != 0) {
[0244] for( x = 0; x < CroppedWidth / SubWidthC; x++ ) {
[0245] for ( y = 0; y < CroppedHeight / SubHeightC; y++ ) {
[0246] inputBaseCb[ x][ y ] = InpC( baseCroppedCbPic[x][ y ] )
[0247] inputBaseCr[ x][ y ] = InpC( baseCroppedCrPic[ x][ y ] )
[0248] }
[0249] }
[0250] }
[0251] When gfv_drive_pic_fusion_flag equals 1, the driving image luminance sample arrays inputDriveY, inputDriveCb, and inputDriveCr are derived as follows:
[0252] for( x = 0; x< CroppedWidth; x++ ) {
[0253] for ( y = 0; y< CroppedHeight; y++ ) {
[0254] inputDriveY[ x ][ y ] = InpY( driveCroppedYPic[ x ][ y] )
[0255] }
[0256] }
[0257] if (ChromaFormatIdc != 0) {
[0258] for( x = 0; x< CroppedWidth / SubWidthC; x++ ) {
[0259] for ( y = 0; y < CroppedHeight / SubHeightC; y++ ) {
[0260] InputDriveCb[ x][ y ] = InpC( driveCroppedCbPic[ x][ y ] )
[0261] InputDriveCr[ x][ y ] = InpC( driveCroppedCrPic[ x ][ y ] )
[0262] }
[0263] }
[0264] }
[0265] When gfv_base_pic_flag equals 0, for the current image, the keypoint coordinate array inputDriveKeyPoint and the matrix inputDriveMatrix are derived as follows:
[0266] for ( i = 0; i < = convNumKeyPoint; i++ ) {
[0267] inputDriveKeyPoint[ i ][ 0 ] = convKeyPoint[ i ][ 0 ]
[0268] inputDriveKeyPoint[ i ][ 1 ] = convKeyPoint[ i ][ 1 ]
[0269] inputDriveKeyPoint[ i ][ 2 ] = convKeyPoint[ i ][ 2 ]
[0270] }
[0271] for( j = 0; j < convNumMatrix; j++ ) {
[0272] for( k=0; k< convMatrixHeight; k++ ) {
[0273] for ( m=0;m< convMatrixWidth; m++) {
[0274] inputDriveMatrix[ j ][ k ][ m ] = convMatrix [ j ][ k ][ m ]
[0275] }
[0276] }
[0277] }
[0278] When gfv_base_pic_flag equals 1, for the base image, the keypoint coordinate array inputBaseKeyPoint and the matrix inputBaseMatrix are derived as follows:
[0279] for ( i = 0; i < = convNumKeyPoint; i++ ) {
[0280] inputBaseKeyPoint[ i ][ 0 ] = convKeyPoint[ i ][ 0 ]
[0281] inputBaseKeyPoint[ i ][ 1 ] = convKeyPoint[ i ][ 1 ]
[0282] inputBaseKeyPoint[ i ][ 2 ] = convKeyPoint[ i ][ 2 ]
[0283] }
[0284] for( j = 0; j < convNumMatrix; j++) {
[0285] for( k=0; k< convMatrixHeight; k++ ) {
[0286] for ( l=0;l< convMatrixWidth; l++) {
[0287] inputBaseMatrix[ j ][ k ][ l ] = convMatrix [ j ][ k ][ l ]
[0288] }
[0289] }
[0290] }
[0291] The functions InpY() and InpC() are defined as follows:
[0292] InpY( x ) = x ÷ ( ( 1 << BitDepthY ) – 1 )
[0293] InpC( x ) = x ÷ ( ( 1 << BitDepthC ) – 1 )
[0294] GenerativeNN() is the process of generating sample values for the output image corresponding to the driving image. This process is only called when gfc_base_pic_flag equals 0. Both the input and output values of GenerativeNN() are real numbers.
[0295] The input to GenerativeNN() is:
[0296] - When gfv_base_pic_flag equals 0, gfv_drive_pic_fusion_flag equals 0, and ChromaFormatIdc equals 0: inputBaseY, inputBaseKeyPoint, inputBaseMatrix, inputDriveKeyPoint, inputDriveMatrix
[0297] - When gfv_base_pic_flag equals 0 and gfv_drive_pic_fusion_flag equals 0 and ChromaFormatIdc is not equal to 0: inputBaseY, inputBaseCb, inputBaseCr, inputBaseKeyPoint, inputBaseMatrix, inputDriveKeyPoint, inputDriveMatrix
[0298] - When gfv_base_pic_flag equals 0, gfv_drive_pic_fusion_flag equals 1, and ChromaFormatIdc equals 0: inputBaseY, inputDriveY, inputBaseKeyPoint, inputBaseMatrix, inputDriveKeyPoint, inputDriveMatrix
[0299] - When gfv_base_pic_flag equals 0 and gfv_drive_pic_fusion_flag equals 1 and ChromaFormatIdc is not equal to 0: inputBaseY, inputBaseCb, inputBaseCr, inputDriveY, inputDriveCb, inputDriveCr, inputBaseKeyPoint, inputBaseMatrix, inputDriveKeyPoint, inputDriveMatrix
[0300] The output of GenerativeNN() is:
[0301] - Luminance sampling array genY
[0302] - When ChromaFormatIdc is not equal to 0, the two chromaticity sample arrays genCb and genCr.
[0303] The procedure StoreOutputTensors() used to derive the output is defined as follows:
[0304] When gfv_base_pic_flag equals 0, the output sample arrays outYPic[x][y], outCbPic[x][y], and outCrPic[x][y] are derived as follows:
[0305] for(x=0; x< CroppedWidth; x++){
[0306] for(y=0; y< CroppedHeight; y++){
[0307] outputYPic[ x ][ y ] = OutY( genY[ x ][ y ] )
[0308] }
[0309] }
[0310] if(ChromaFormatIdc != 0) {
[0311] for(x=0; x< CroppedWidth / SubWidthC; x++){
[0312] for(y=0; y< CroppedHeight / SubHeightC; y++){
[0313] outputCbPic[ x ][ y ] = OutC( genCb[ x ][ y ] )
[0314] outputCrPic[ x][ y ] = OutC( genCr[ x ][ y ] )
[0315] }
[0316] }
[0317] }
[0318] When gfv_base_pic_flag equals 1, the output sample arrays outYPic[x][y], outCbPic[x][y], and outCrPic[x][y] are derived as follows:
[0319] for(x=0; x< CroppedWidth; x++){
[0320] for(y=0; y< CroppedHeight; y++){
[0321] outputYPic[ x ][ y ] = baseCroppedYPic [ x ][ y ]
[0322] }
[0323] }
[0324] if(ChromaFormatIdc != 0) {
[0325] for(x=0; x< CroppedWidth / SubWidthC; x++){
[0326] for(y=0; y< CroppedHeight / SubHeightC; y++){
[0327] outputCbPic[x][y] = baseCbPic[x][y]
[0328] outputCrPic[x][y] = baseCroppedCbPic[x][y]
[0329] }
[0330] }
[0331] }
[0332] The functions OutY() and OutC() are defined as follows:
[0333] OutY( x ) = Clip3( 0, ( 1 << BitDepthY ) – 1 , x ( ( 1 << BitDepthY) – 1 )
[0334] OutC( x ) = Clip3( 0, ( 1 << BitDepthC ) – 1 , x ( ( 1 << BitDepthC) – 1 )
[0335] 4. The technical problem solved by the disclosed technical solution
[0336] First, GFV SEI does not support multiple basic image inputs.
[0337] Second, GFV SEI does not support digital human videos.
[0338] Third, GFV SEI does not support multiple digital humans.
[0339] 5. List of solutions and implementation examples
[0340] To address the aforementioned issues, 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.
[0341] 1) To solve problem 1, multiple base images can be considered in the generative model.
[0342] a. In one example, one or more syntax elements can be added or modified to indicate the number of input images for the generated model.
[0343] b. In one example, such as based on explicit signaling or the output order of earlier decoded images, deduce the list of input images for the generative model.
[0344] c. In one example, one or more syntax elements can be added or modified to indicate whether the current image is an input and / or the order of the current image in the list of input images.
[0345] d. In one example, the basic image and the non-basic image can be indicated in different ways. For example, in an SEI message, only the non-basic image can be indicated.
[0346] i. Optionally, further, an indication of which basic images should be used together with non-basic images can be transmitted / derived in the SEI message via signal transmission.
[0347] 2) To solve problem 2, GFV SEI messages can be extended to support the encoding, decoding, and transmission of digital human videos.
[0348] a. In one example, one or more syntax elements can be added or modified to indicate whether the video is a digital human video.
[0349] b. In one example, one or more syntax elements can be added or modified to indicate specific feature metadata of the digital human video.
[0350] i. In one example, voice data and / or voice features can be added to drive video generation.
[0351] ii. In one example, text data can be added to drive video generation.
[0352] iii. In one example, skeletal features (e.g., including keypoint features and motion features from the base image) can be added to drive video generation.
[0353] c. In one example, a key video set can be sent and indicated in an SEI message.
[0354] i. In one example, one or more syntax elements can be added or modified to indicate whether the current image belongs to a specific key video set.
[0355] d. In one example, the generative network can take a set of videos and feature metadata associated with the digital human videos as input to generate videos.
[0356] e. Optionally, one or more new SEI messages may be specified to support digital human video.
[0357] i. In one example, it can be specified to generate human video SEI messages.
[0358] f. In the example above, relevant information can be transmitted via signaling in a specific SEI message (rather than in the current GFV SEI message).
[0359] 3) To address problem 3, GFV SEI messages can be extended to support digital human video, encoding / decoding, and transmission with multiple digital humans.
[0360] a) In one example, a facial ID or human ID can be added to indicate the corresponding digital human, thereby driving the generation of videos with multiple digital humans.
[0361] 4) The above items and sub-items can be applied to other video types, such as digital animal videos, general videos, and combinations thereof.
[0362] 6. References
[0363] [1]ITU-T and ISO / IEC, “High efficiency video coding,” Rec. ITU-TH.265 | ISO / IEC 23008-2 (in force edition).
[0364] [2]J. Chen, E. Alshina, GJ Sullivan, J.-R. Ohm, J. Boyce, "Algorithm description of Joint Exploration Test Model 7 (JEM7)," JVET-G1001, Aug. 2017.
[0365] [3]Rec. ITU-T H.266 | ISO / IEC 23090-3, “Versatile Video Coding,”2022.
[0366] [4]Rec. ITU-T Rec. H.274 | ISO / IEC 23002-7, “Versatile SupplementalEnhancement Information Messages for Coded Video Bitstreams,” 2022.
[0367] [5]S. McCarthy, J. Chen, S. Deshpande, M. M. Hannuksela, Hendry, G.J. Sullivan, and Y.-K. Wang (editors), “SEI messages for VSEI version 4(Draft 1),” JVET output document JVET-ACG2034, publicly available onlineherein: https: / / jvet-experts.org / doc_end_user / documents / 33_Teleconference / wg11 / JVET-AG2034-v1.zip.
[0368] [6]S. McCarthy, J. Chen, S. Deshpande, M. M. Hannuksela, Hendry,“Technologies under consideration for future extensions of VSEI (version 3),”JVET output document JVET-ACG2032, publicly available online herein: https: / / jvet-experts.org / doc_end_user / documents / 33_Teleconference / wg11 / JVET-AG2032-v1.zip.
[0369] Figure 2This 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 Networking (PON), etc.) and wireless interfaces (such as Wi-Fi or cellular interfaces).
[0370] 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 / decoded) representation of the video received at input 4002, whether stored or transmitted, may be used by component 4008 to generate pixel values or displayable video to be sent 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.
[0371] 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.
[0372] Figure 3This 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(multiple) 4102 may be configured to implement one or more methods described herein. The memories(multiple) 4104 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, such as a graphics coprocessor.
[0373] Figure 4 This is a flowchart of an example method 4200 for video processing. Method 4200 determines in step 4202 to consider multiple base images in the generation model. In step 4204, a conversion between visual media data and a bitstream is performed based on the multiple base images. The conversion may include encoding at the encoder, decoding at the decoder, or a combination thereof.
[0374] It should be noted that method 4200 can be implemented in a means of 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 4200. Furthermore, method 4200 can be executed by a non-transitory computer-readable medium, which includes 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 4200 when executed by a processor.
[0375] Figure 5 This is a block diagram illustrating an example video encoding / decoding system 4300 from which the techniques of this disclosure can be utilized. 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, and this 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, and this target device 4320 may be referred to as a video decoding device.
[0376] 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 coded representation of the video data. The bitstream may include encoded pictures and associated data. Encoded pictures are coded 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.
[0377] 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.
[0378] The video encoder 4314 and the video decoder 4324 can operate according to video compression standards, such as HEVC, VVM and other existing and / or further standards.
[0379] Figure 6 This is a block diagram illustrating an example of a video encoder 4400, wherein the video encoder 4400 may be... Figure 5 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.
[0380] 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.
[0381] 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.
[0382] Furthermore, some components such as the motion estimation unit 4404 and the motion compensation unit 4405 can be highly integrated, but for illustrative purposes, these components are represented separately in the example of the video encoder 4400.
[0383] 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.
[0384] 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).
[0385] 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.
[0386] 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.
[0387] In some examples, motion estimation unit 4404 can perform unidirectional prediction on the current video block, and can search for a reference video block for the current video block in the reference images of list 0 or list 1. Motion estimation unit 4404 can then generate a reference index indicating the reference image containing the reference video block in list 0 or list 1, 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.
[0388] In other examples, motion estimation unit 4404 can perform bidirectional prediction on the current video block. Motion estimation unit 4404 can search for a reference video block for the current video block in the reference images of list 0, and can also search for another reference video block for the current video block in the reference images of list 1. 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.
[0389] 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.
[0390] 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.
[0391] 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.
[0392] 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 Pattern Signaling.
[0393] 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.
[0394] 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.
[0395] 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.
[0396] 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.
[0397] 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.
[0398] 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 samples 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.
[0399] 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.
[0400] The entropy encoding unit 4414 can receive data from other functional components of the video encoder 4400. When the 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.
[0401] Figure 7 This is a block diagram illustrating an example of a video decoder 4500, wherein the video decoder 4500 may be... Figure 5 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.
[0402] 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 generally contrasted with the encoding process described with respect to the video encoder 4400.
[0403] 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.
[0404] The motion compensation unit 4502 can generate motion compensation blocks, possibly performing 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.
[0405] The motion compensation unit 4502 can use the interpolation filter used by the video encoder 4400 during the encoding of a video block to calculate the interpolation for sub-integer pixels of the 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.
[0406] 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.
[0407] Intra-prediction unit 4503 can use, for example, an intra-prediction mode received in the bitstream to form prediction blocks from spatially adjacent blocks. Dequantization unit 4504 dequantizes (i.e., dequantizes) the quantized video block coefficients provided in the bitstream and decoded by entropy decoding unit 4501. Inverse transform unit 4505 applies the inverse transform.
[0408] 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 applied to 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.
[0409] Figure 8 This is a schematic diagram of the 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 offsets and applying finite impulse response (FIR) filters, and by utilizing encoding / decoding side information through signal transmission offsets 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.
[0410] 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 ALF4606 for filtering before these images are stored in reference image buffer 4612.
[0411] Figure 9 This is a flowchart of an example method 4700 for video processing. In step 4702, method 4700 determines that multiple base images are used in a generative model including a generative network. For digital human videos, the generative network uses Generative Face Video (GFV) Supplemental Enhancement Information (SEI) messages to encode and decode video information. In step 4704, a conversion between visual media data and a bitstream is performed based on the GFV SEI messages. The conversion may include encoding at the encoder, decoding at the decoder, or a combination thereof.
[0412] 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, which includes 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.
[0413] The following is a list of some preferred solutions.
[0414] The following solutions illustrate examples of the techniques discussed in this article.
[0415] 1. A method for processing media data, comprising: determining a plurality of basic images to be considered in a generative model; and performing a conversion between visual media data and a bitstream based on the plurality of basic images.
[0416] 2. The method according to Solution 1, wherein one or more syntax elements are used to indicate the number of input images for the generative model.
[0417] 3. The method according to any one of solutions 1-2, wherein the list of input images for the generative model is derived based on explicit signaling or based on the output order of earlier decoded images.
[0418] 4. The method according to any one of solutions 1-3, wherein one or more syntax elements are added or modified to indicate whether the current image is an input or the current image order in the list of input images.
[0419] 5. The method according to any one of solutions 1-4, wherein the basic image and the non-basic image are indicated in different ways.
[0420] 6. The method according to any one of solutions 1-5, wherein only non-basic images are indicated in the supplementary enhancement information (SEI) message.
[0421] 7. The method according to any one of solutions 1-6, wherein the SEI message contains an indication, either by signal transmission or by inferring from the SEI message, which basic images are to be used together with the non-basic images.
[0422] 8. The method according to any one of solutions 1-7, wherein a facial video (GFV) SEI message is generated to support the encoding, decoding and transmission of digital human video.
[0423] 9. The method according to any one of solutions 1-8, wherein one or more syntactic elements are used to indicate whether the video is a digital human video.
[0424] 10. The method according to any one of solutions 1-9, wherein one or more syntax elements are used to indicate specific feature metadata of a digital human video.
[0425] 11. The method according to any one of solutions 1-10, wherein video generation is driven by speech data or speech feature data, or wherein video generation is driven by text data, or wherein video generation is driven by skeletal features including key point features and motion features of a base image.
[0426] 12. The method according to any one of solutions 1-11, wherein a key video set is sent and indicated in the SEI message, or wherein one or more syntax elements are used to indicate whether the current image belongs to a specific key video set.
[0427] 13. The method according to any one of solutions 1-12, wherein the generating network takes a video set and feature metadata related to the digital human video as input to generate a video.
[0428] 14. The method according to any one of solutions 1-13, wherein one or more new SEI messages are specified to support digital human video, or wherein a human video SEI message is specified to generate.
[0429] 15. The method according to any one of solutions 1-14, wherein the feature metadata information related to the digital human video is transmitted via signaling in a specific SEI message, rather than via signaling in a GFV SEI message.
[0430] 16. The method according to any one of solutions 1-15, wherein the GFV SEI message supports digital human video with multiple digital humans, encoding, decoding and transmission, or wherein a facial identifier (ID) or human ID is added to indicate the corresponding digital human, thereby driving the generation of video with multiple digital humans.
[0431] 17. The method according to any one of solutions 1-16, wherein the visual media data includes digital human videos, digital animal videos, general videos, or combinations thereof.
[0432] 18. The method according to any one of solutions 1-17, wherein the conversion includes encoding the visual media data into the bitstream.
[0433] 19. The method according to any one of solutions 1-17, wherein the conversion includes decoding the visual media data from the bitstream.
[0434] 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 described in any one of solutions 1-19.
[0435] 21. A non-transitory computer-readable medium comprising a computer program product for use by a video codec apparatus, the computer program product comprising computer-executable instructions stored on the non-transitory computer-readable medium such that, when executed by a processor, the video codec apparatus performs the method described in any one of solutions 1-19.
[0436] 22. A non-transitory computer-readable recording medium storing a bitstream of video generated by a method performed by a video processing apparatus, wherein the method includes: determining a plurality of basic images to be considered in a generation model; and generating the bitstream based on the determination.
[0437] 23. A method for storing a bitstream of video, comprising: determining a plurality of basic images to be considered in a generative model; generating the bitstream based on the determination; and storing the bitstream in a non-transitory computer-readable recording medium.
[0438] 24. A method, apparatus, or system described in this document.
[0439] The following solutions illustrate other examples of the techniques discussed in this article.
[0440] 1. A method for processing media data, comprising: determining multiple base images to be used in a generative model including a generative network for a digital human video, said generative network encoding and decoding video information using Generative Face Video (GFV) Supplemental Enhancement Information (SEI) messages; and performing a conversion between visual media data and a bitstream based on said GFV SEI messages.
[0441] 2. The method according to Solution 1, wherein one or more syntax elements in the GFV SEI message are used to indicate the number of input images for the generative model.
[0442] 3. The method according to any one of solutions 1-2, wherein the list of input images for the generative model is derived based on explicit signaling or based on the output order of earlier decoded images.
[0443] 4. The method according to any one of solutions 1-3, wherein one or more syntax elements indicate whether the current image is an input or the current image order in a list of input images.
[0444] 5. The method according to any one of solutions 1-4, wherein the basic image and the non-basic image are indicated differently in the GFV SEI message.
[0445] 6. The method according to any one of solutions 1-5, wherein only non-basic images are indicated in the GFV SEI message.
[0446] 7. The method according to any one of solutions 1-6, wherein one or more identifiers are transmitted via signaling in the GFV SEI message, the identifiers indicating which primary images are used together with which non-primary images.
[0447] 8. The method according to any one of solutions 1-7, wherein one or more identifiers are derived based on the GFV SEI message, the identifiers indicating which basic images are used together with which non-basic images.
[0448] 9. The method according to any one of solutions 1-8, wherein one or more syntax elements in the GFV SEI message are used to indicate whether the video information is a digital human video.
[0449] 10. The method according to any one of solutions 1-9, wherein one or more syntax elements are used to indicate specific feature metadata of a digital human video.
[0450] 11. The method according to any one of solutions 1-10, wherein video generation is driven by speech data, speech feature data, text data, or skeletal features including key point features and motion features of a base image.
[0451] 12. The method according to any one of solutions 1-11, wherein the key video set is included in the bitstream, and wherein the key video set is indicated in the GFV SEI message, or wherein one or more syntax elements in the GFV SEI message indicate whether the current picture is included in a particular key video set.
[0452] 13. The method according to any one of solutions 1-12, wherein the generating network receives a video set and feature metadata related to the digital human video as input to generate the video.
[0453] 14. The method according to any one of solutions 1-13, wherein one or more SEI messages are specified to support digital human video.
[0454] 15. The method according to any one of solutions 1-14, wherein the generation of human video SEI messages is specified to support digital human videos.
[0455] 16. The method according to any one of solutions 1-15, wherein digital human video-related feature metadata information is transmitted via signaling in a specific SEI message other than the GFV SEI message.
[0456] 17. The method according to any one of solutions 1-16, wherein the GFV SEI message supports the encoding, decoding and transmission of digital human videos with multiple digital humans.
[0457] 18. The method according to any one of solutions 1-17, wherein the GFV SEI message includes a facial identifier (ID) or human ID to indicate the corresponding digital human, thereby driving the generation of a video with multiple digital humans.
[0458] 19. The method according to any one of solutions 1-18, wherein the visual media data includes digital human videos, digital animal videos, general videos, or combinations thereof.
[0459] 20. The method according to any one of solutions 1-19, wherein the conversion includes encoding the visual media data into the bitstream.
[0460] 21. The method according to any one of solutions 1-19, wherein the conversion includes decoding the visual media data from the bitstream.
[0461] 22. 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 described in any one of solutions 1-21.
[0462] 23. A non-transitory computer-readable medium comprising a computer program product for use by a video codec apparatus, the computer program product comprising computer-executable instructions stored on the non-transitory computer-readable medium such that, when executed by a processor, the video codec apparatus performs the method described in any one of solutions 1-21.
[0463] 24. A non-transitory computer-readable recording medium storing a bitstream of video generated by a method performed by a video processing apparatus, wherein the method comprises: determining the use of a plurality of basic images in a generative model including a generative network, the generative network employing Generative Face Video (GFV) Supplemental Enhancement Information (SEI) messages to encode and decode video information for a digital human video; and generating the bitstream based on the determination.
[0464] 25. A method for storing a bitstream of video, comprising: determining multiple base images in a generative model including a generative network for a digital human video, the generative network encoding and decoding video information using Generative Face Video (GFV) Supplemental Enhancement Information (SEI) messages; generating the bitstream based on the determination; and storing the bitstream in a non-transitory computer-readable recording medium.
[0465] 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, based on the format rules, to generate the decoded video.
[0466] 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 resolve the bitstream based on 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 the encoded / decoded representation accordingly by including or excluding syntax fields from the encoded / decoded representation.
[0467] 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 a combination of one or more. 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 a data processing apparatus or for controlling the operation of the 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 of one or more. The term "data processing apparatus" includes 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 code that creates an execution environment for an associated computer program, such as code constituting processor firmware, a protocol stack, a database management system, an operating system, or a combination of one or more. 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.
[0468] 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.
[0469] 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 circuits, and the devices can be implemented as special-purpose logic circuits, such as field-programmable gate arrays (FPGAs) or application-specific integrated circuits (ASICs).
[0470] Processors suitable for executing computer programs include, for example, general-purpose and special-purpose microprocessors, and any one or more processors of any type of digital computer. Typically, a 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, or receive data from or transfer data to one or more mass storage devices via operative coupling, or both. 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. Processors and memory may be supplemented by or incorporated into special-purpose logic circuitry.
[0471] 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.
[0472] 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.
[0473] 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.
[0474] When there is no intermediate component (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 is an intermediate component between the first and second components other than a line, trace, or other medium, 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.
[0475] 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 to be considered illustrative rather than restrictive and are not intended to be limited to the details set forth herein. For example, various elements or components may be combined or integrated into another system, or certain features may be omitted or not implemented.
[0476] Furthermore, the technologies, systems, subsystems, and methods described and illustrated as discrete or separate in the various embodiments can be combined or integrated with other systems, modules, technologies, or methods without departing from the scope of this disclosure. Other items shown or discussed as couplings can be directly connected or indirectly coupled or communicated through some interface, device, or intermediate component (whether electrical, mechanical, or other). Other examples of variations, substitutions, and modifications can be determined by those skilled in the art and can be made without departing from the spirit and scope of this disclosure.
Claims
1. A method for processing media data, comprising: The generative model, which includes a generative network, utilizes multiple base images. For digital human videos, the generative network employs Generative Face Video (GFV) Supplementary Enhancement Information (SEI) messages to encode and decode video information. The conversion between visual media data and bitstream is performed based on the GFV SEI message.
2. The method according to claim 1, wherein, One or more syntax elements in the GFV SEI message are used to indicate the number of input images for the generative model.
3. The method according to any one of claims 1-2, wherein, The list of input images for the generative model is derived based on explicit signaling or the output order of earlier decoded images.
4. The method according to any one of claims 1-3, wherein, One or more syntax elements indicate whether the current image is an input or the current image in the list of input images.
5. The method according to any one of claims 1-4, wherein, The basic image and non-basic images are indicated differently in the GFVSEI message.
6. The method according to any one of claims 1-5, wherein, The GFV SEI message only indicates non-basic images.
7. The method according to any one of claims 1-6, wherein, The GFV SEI message transmits one or more identifiers via signaling, which indicate which primary images are used together with which non-primary images.
8. The method according to any one of claims 1-7, wherein, One or more identifiers are derived based on the GFV SEI message, which indicate which basic images are used together with which non-basic images.
9. The method according to any one of claims 1-8, wherein, One or more syntax elements in the GFV SEI message are used to indicate whether the video information is a digital human video.
10. The method according to any one of claims 1-9, wherein, One or more syntax elements are used to indicate specific feature metadata of a digital human video.
11. The method according to any one of claims 1-10, wherein, Video generation is driven by speech data, speech feature data, text data, or skeletal features that include keypoint features and motion features of the base image.
12. The method according to any one of claims 1-11, wherein, The key video set is included in the bitstream, and the key video set is indicated in the GFV SEI message, or one or more syntax elements in the GFV SEI message indicate whether the current image is included in a specific key video set.
13. The method according to any one of claims 1-12, wherein, The generating network receives feature metadata related to video sets and digital human videos as input to generate videos.
14. The method according to any one of claims 1-13, wherein, Specify one or more SEI messages to support digital human videos.
15. The method according to any one of claims 1-14, wherein, The specification specifies the generation of human video SEI messages to support digital human videos.
16. The method according to any one of claims 1-15, wherein, In a specific SEI message other than the GFV SEI message, feature metadata information related to the digital human video is transmitted via signaling.
17. The method according to any one of claims 1-16, wherein, The GFV SEI message supports the encoding, decoding, and transmission of digital human videos with multiple digital humans.
18. The method according to any one of claims 1-17, wherein, The GFV SEI message includes a facial identifier (ID) or human ID to indicate the corresponding digital human, thereby driving the generation of videos with multiple digital humans.
19. The method according to any one of claims 1-18, wherein, The visual media data includes digital human videos, digital animal videos, general videos, or combinations thereof.
20. The method according to any one of claims 1-19, wherein, The conversion includes encoding the visual media data into the bitstream.
21. The method according to any one of claims 1-19, wherein, The conversion includes decoding the visual media data from the bitstream.
22. An apparatus for processing video data, comprising: processor; and a non-transitory memory thereon having instructions, wherein, when executed by the processor, the instructions cause the processor to perform the method of any one of claims 1-21.
23. A non-transitory computer-readable medium comprising a computer program product for use by a video codec apparatus, the computer program product comprising computer-executable instructions stored on the non-transitory computer-readable medium such that, when executed by a processor, the video codec apparatus performs the method of any one of claims 1-21.
24. A non-transitory computer-readable recording medium storing a bitstream of video generated by a method performed by a video processing apparatus, wherein, The method includes: The generative model, which includes a generative network, utilizes multiple base images. For digital human videos, the generative network employs Generative Face Video (GFV) Supplementary Enhancement Information (SEI) messages to encode and decode video information. The bit stream is generated based on the determination.
25. A method for storing a bitstream of video, comprising: The generative model, which includes a generative network, uses multiple base images for digital human videos. The generative network uses Generative Face Video (GFV) Supplemental Enhancement Information (SEI) messages to encode and decode video information. The bit stream is generated based on the determination; as well as The bit stream is stored in a non-transitory computer-readable recording medium.
