Patents by Inventor Kui Wang

Kui Wang has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • METHOD, DEVICE, AND MEDIUM FOR VIDEO PROCESSING
    Publication number: 20240244219
    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: receiving, by a first device, a metadata file from a server; and determining, from the metadata file, a list of region identities (IDs) for indicating a first set of coded video data units in each picture of a first video representing a target picture-in-picture region which is able to be replaced by a second set of coded video units in a second video.
    Type: Application
    Filed: March 27, 2024
    Publication date: July 18, 2024
    Inventor: Ye-Kui WANG
  • METHOD, APPARATUS, AND MEDIUM FOR VIDEO PROCESSING
    Publication number: 20240244158
    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing comprises: performing a conversion between a media file of a first video and a bitstream of the first video, wherein the media file comprises a first indication indicating whether a first set of coded video data units representing a target picture-in-picture region in the first video are replaceable by a second set of coded video data units associated with a second video. The proposed method advantageously makes it possible to support picture-in-picture services in a media file based on ISO base media file format (ISOBMFF).
    Type: Application
    Filed: March 27, 2024
    Publication date: July 18, 2024
    Inventor: Ye-Kui WANG
  • Reference Picture Management in Video Coding
    Publication number: 20240244184
    Abstract: A method of decoding a coded video bitstream is provided. The method includes parsing a slice header of a current slice represented in the coded video bitstream. The slice header includes a reference picture list structure. The method also includes deriving, based on the reference picture list structure, a reference picture list of the current slice; and obtaining, based on the reference picture list, at least one reconstructed block of the current slice.
    Type: Application
    Filed: March 5, 2024
    Publication date: July 18, 2024
    Inventors: Ye-Kui Wang, FNU Hendry
  • METHOD, APPARATUS, AND MEDIUM FOR VIDEO PROCESSING
    Publication number: 20240244159
    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing comprises: performing a conversion between a media file of a first video and a bitstream of the first video, wherein the media file comprises an indication indicating that a first track carrying the bitstream of the first video and a second track carrying a bitstream of a second video are a track pair for providing a picture-in-picture service. The proposed method advantageously makes it possible to support picture-in-picture services in a media file based on ISO base media file format (ISOBMFF).
    Type: Application
    Filed: March 27, 2024
    Publication date: July 18, 2024
    Inventor: Ye-Kui WANG
  • METHOD, APPARATUS AND MEDIUM FOR VIDEO PROCESSING
    Publication number: 20240244245
    Abstract: Embodiments of the present disclosure provide a solution for video processing. The method comprises: performing a conversion between a target video block of a video and a bitstream of the video according to a decoding conformance constraint. The decoding conformance constraint specifies that a decoder conforming to a first profile is capable of decoding of the bitstream when at least one condition applies. The at least one condition comprises a first condition that the bitstream is indicated to conform to at least one second profile. The first profile corresponds to a first bit depth and a first relative sample rate of color components of video samples. The at least one second profile corresponds to a second bit depth different from the first bit depth and a second relative sample rate of color components of video samples, which is the same as the first relative sample rate.
    Type: Application
    Filed: March 29, 2024
    Publication date: July 18, 2024
    Inventor: Ye-Kui WANG
  • Gradual Decoding Refresh In Video Coding
    Publication number: 20240244189
    Abstract: A method of decoding a coded video bitstream implemented by a video decoder is provided. The method includes the video decoder determining whether a value for a first flag is provided by an external input; setting a first flag equal to the value provided by the external input and a second flag equal to the value of the first flag to prevent a gradual decoding refresh (GDR) picture from being output when the value for the first flag is provided by the external input; decoding the GDR picture; and storing the GDR picture in a decoded picture buffer (DPB).
    Type: Application
    Filed: January 22, 2024
    Publication date: July 18, 2024
    Inventors: FNU Hendry, Ye-Kui Wang, Jianle Chen
  • METHOD, DEVICE, AND MEDIUM FOR VIDEO PROCESSING
    Publication number: 20240244303
    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: receiving, at a first device, a metadata file from a second device; and determining a descriptor in a data structure in the metadata file, a presence of the descriptor indicating that the data structure is for providing a picture-in-picture service, and the data structure indicating a selection of a first set of bitstreams of a first video and a second set of bitstreams of a second video for the picture-in-picture service.
    Type: Application
    Filed: March 27, 2024
    Publication date: July 18, 2024
    Inventor: Ye-Kui WANG
  • METHOD, APPARATUS, AND MEDIUM FOR VIDEO PROCESSING
    Publication number: 20240244234
    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing comprises: performing a conversion between a media file of a video and a bitstream of the video, wherein the media file comprises a data structure indicating video decoder initialization information (VDII) for decoding the bitstream, the data structure being at a level higher than a track level. Compared with the conventional solution, the VDII can be signaled more efficiently.
    Type: Application
    Filed: April 1, 2024
    Publication date: July 18, 2024
    Inventor: Ye-Kui WANG
  • Coding of pictures containing slices and tiles
    Patent number: 12041237
    Abstract: Techniques for video processing, including video coding, video decoding and video transcoding are described. One example method includes performing a conversion between a video picture that includes one or more tiles and one or more rectangular slices and a bitstream of the video according to a rule. The rule specifies that, for iteratively determining information about the one or more rectangular slices, a variable indicating a tile index is updated only for slices having indices that are smaller than a value equal to a number of slices in the video picture minus 1.
    Type: Grant
    Filed: August 19, 2022
    Date of Patent: July 16, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Kai Zhang, Li Zhang, Ye-kui Wang, Zhipin Deng, Kui Fan, Jizheng Xu, Hongbin Liu
  • Interlaced video coding with leading pictures
    Patent number: 12041256
    Abstract: A video coding mechanism is disclosed. The mechanism includes receiving a bitstream comprising a flag and a plurality of coded pictures including an intra random access point (IRAP) picture and one or more non-leading pictures associated with the IRAP picture. When the flag is set to a first value any leading pictures associated with the IRAP picture precede, in decoding order, all non-leading pictures associated with the IRAP picture. When the flag is set to a second value a non-leading picture precedes, in decoding order, an initial leading picture associated with the IRAP picture. The IRAP picture, any leading pictures associated with the IRAP picture, and the one or more non-leading pictures associated with the IRAP picture are decoded in decoding order based on the flag.
    Type: Grant
    Filed: October 1, 2021
    Date of Patent: July 16, 2024
    Assignee: Huawei Technologies Co., Ltd.
    Inventors: Fnu Hendry, Ye-Kui Wang
  • Signalling of weights of a reference picture list
    Patent number: 12041257
    Abstract: A method includes performing a conversion, according to a rule, between a current slice of a current picture of a video and a bitstream of the video, wherein the rule specifies that a first syntax element of a picture parameter set (PPS) and a second syntax element of the PPS control whether a third syntax element is included in the bitstream, and wherein the first syntax element indicates whether a weighted prediction is enabled for bi-directional slices of coded pictures referring to the PPS, the second syntax element indicates whether information related to the weighted prediction is present in picture headers or slice headers of coded pictures referring to the PPS, and the third syntax element indicates a number of weights associated with a reference picture list 1 of the current slice.
    Type: Grant
    Filed: August 17, 2022
    Date of Patent: July 16, 2024
    Assignee: Bytedance Inc.
    Inventors: Ye-kui Wang, Li Zhang
  • Dependent random access point indication in video bitstreams
    Patent number: 12041386
    Abstract: Systems, methods and apparatus for encoding, decoding or transcoding visual media data are described. One example method of processing visual media data includes performing a conversion between visual media data and a bitstream of the visual media data according to a format rule, wherein the format rule specifies whether and how a second type of supplemental enhancement information (SEI) message that is different from a first type of SEI message is included in the bitstream, and wherein the first type of the SEI message and the second type of the SEI message indicate a first type of dependent random access point (DRAP) picture and a second type of DRAP picture, respectively.
    Type: Grant
    Filed: September 24, 2021
    Date of Patent: July 16, 2024
    Assignee: Lemon Inc.
    Inventor: Ye-Kui Wang
  • Mixed NAL unit picture constraints in video coding
    Patent number: 12041249
    Abstract: A video coding mechanism is disclosed. The mechanism includes receiving a bitstream comprising a current picture including a plurality of video coding layer (VCL) network abstraction layer (NAL) units that do not have a same NAL unit type. Active entries of reference picture lists are obtained for slices positioned in a sub-picture A (subpicA) in subsequent pictures following the current picture in decoding order. The active entries do not refer to any reference picture preceding the current picture in decoding order when the subpicA at the current picture is associated with an intra-random access point (IRAP) NAL unit type. The subsequent pictures are decoded based on the reference picture list active entries. The subsequent pictures are forwarded for display as part of a decoded video sequence.
    Type: Grant
    Filed: January 4, 2022
    Date of Patent: July 16, 2024
    Assignee: Huawei Technologies Co., Ltd.
    Inventors: Ye-Kui Wang, FNU Hendry
  • SEI message for single layer OLS
    Patent number: 12041254
    Abstract: A video coding mechanism is disclosed. The mechanism includes encoding a bitstream comprising one or more output layer sets (OLSs). A non-scalable-nested supplemental enhancement information (SEI) message is also encoded into the bitstream. The non-scalable-nested SEI message is constrained to apply only to a zeroth (0-th) OLS. The 0-th OLS includes only an output layer. A set of bitstream conformance tests are performed on the 0-th OLS based on the non-scalable-nested SEI message. The bitstream is stored for communication toward a decoder.
    Type: Grant
    Filed: March 24, 2022
    Date of Patent: July 16, 2024
    Assignee: Huawei Technologies Co., Ltd.
    Inventor: Ye-Kui Wang
  • Video Coding Bitstream Extraction With Identifier Signaling
    Publication number: 20240236376
    Abstract: A video coding mechanism is disclosed. The mechanism includes receiving an extracted bitstream that is a result of a sub-bitstream extraction process from an input bitstream containing a set of sub-pictures. The extracted bitstream contains only a subset of the sub-pictures of the input bitstream to the sub-bitstream extraction process. A flag from the extracted bitstream is set to indicate that sub-picture information related to the subset of the sub-pictures is present in the extracted bitstream. One or more sub-picture identifiers (IDs) for the subset of the sub-pictures are obtained based on the flag. The subset of the sub-pictures is decoded based on the sub-picture IDs.
    Type: Application
    Filed: October 25, 2023
    Publication date: July 11, 2024
    Inventors: Ye-Kui Wang, FNU Hendry
  • Conditional signaling of syntax elements in a picture header
    Patent number: 12034975
    Abstract: A video processing method includes performing a conversion between a video including one or more pictures and a bitstream of the video. The bitstream conforms to a format rule specifying that one or more syntax elements indicative of coding information are selectively included in a picture parameter set of the bitstream responsive to whether it is indicated that each picture referring to the picture parameter set includes a single slice.
    Type: Grant
    Filed: August 29, 2022
    Date of Patent: July 9, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Ye-Kui Wang, Zhipin Deng, Li Zhang, Kai Zhang, Jizheng Xu
  • Interpolation filter clipping for sub-picture motion vectors
    Patent number: 12028517
    Abstract: A video coding mechanism is disclosed. The mechanism includes receiving a bitstream comprising a current picture including a sub-picture coded according to inter-prediction. A motion vector for a block of the sub-picture is determined. A clipping function is applied to sample locations in a reference block to support application of an interpolation filter when the motion vector points outside of the sub-picture and when a flag is set to indicate the sub-picture is treated as a picture. The interpolation filter is applied to results of the clipping function to obtain a predicted sample value. The block is decoded based on the predicted sample value. The block is forwarded for display as part of a decoded video sequence.
    Type: Grant
    Filed: September 9, 2021
    Date of Patent: July 2, 2024
    Assignee: Huawei Technologies Co., Ltd.
    Inventors: Ye-Kui Wang, Jianle Chen, Fnu Hendry
  • Reference Picture Management in Video Coding
    Publication number: 20240214555
    Abstract: A method of decoding a coded video bitstream is provided. The method includes parsing a parameter set represented in the coded video bitstream. The parameter set contains a set of syntax elements that include a set of reference picture list structures. The method also includes parsing a slice header of a current slice represented in the coded video bitstream. The slice header contains an index of a reference picture list structure among the set of reference picture list structures in the parameter set. The method further includes deriving, based on the set of syntax elements in the parameter set and the index of the reference picture list structure, a reference picture list of the current slice. The method also includes obtaining, based on the reference picture list, at least one reconstructed block of the current slice.
    Type: Application
    Filed: February 28, 2024
    Publication date: June 27, 2024
    Inventors: Ye-Kui Wang, FNU Hendry
  • Recovery point signaling in video coding
    Patent number: 12022064
    Abstract: A video coding mechanism is disclosed. The mechanism includes receiving a bitstream comprising a gradual decoding refresh (GDR) picture, a recovery point picture following the GDR picture in decoding order, and a header associated with the GDR picture. The header includes a picture order count (POC) least significant bit (LSB) value coded prior to a recovery POC value. A POC for the GDR picture is determined based on the POC LSB value. The recovery POC value is determined based on the POC for the GDR picture. The recovery POC value indicates a POC for the recovery point picture. The bitstream is decoded according to GDR based on the GDR picture and the recovery point picture.
    Type: Grant
    Filed: November 5, 2021
    Date of Patent: June 25, 2024
    Assignee: Huawei Technologies Co., Ltd.
    Inventor: Ye-Kui Wang
  • Handling of decoder-side motion vector refinement (DMVR) coding tool for reference picture resampling in video coding
    Patent number: 12022107
    Abstract: A method of decoding includes determining, by the video decoder, whether a resolution of a current picture being decoded is the same as the resolution of reference pictures identified by a reference picture list associated with the current picture; enabling, by the video decoder, decoder-side motion vector refinement (DMVR) for a current block of the current picture when the resolution of the current picture is determined to be the same as the resolution of each of the reference pictures; disabling, by the video decoder, the DMVR for the current block of the current picture when the resolution of the current picture is determined to be different than the resolution of either of the reference pictures; and refining, by the video decoder, motion vectors corresponding to the current block using the DMVR when the DMVR flag is enabled for the current block.
    Type: Grant
    Filed: September 24, 2021
    Date of Patent: June 25, 2024
    Assignee: Huawei Technologies Co., Ltd.
    Inventors: Jianle Chen, Fnu Hendry, Ye-Kui Wang