Patents by Inventor Ru-Ling Liao

Ru-Ling Liao 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).

  • Patent number: 12786440
    Abstract: The present disclosure provides methods and apparatuses for processing chroma sampled pictures. An exemplary video processing method includes: determining whether a chroma component is included in a sequence of frames; and in response to a determination that the chroma component is included in the sequence, activating a sub-process for processing the sequence, wherein the sub-process comprises one or more of joint coding for chroma residues (JCCR), block differential pulse coded modulation (BDPCM), palette mode, or adaptive color transform (ACT).
    Type: Grant
    Filed: September 4, 2024
    Date of Patent: November 3, 2026
    Assignee: HFI INNOVATION INC.
    Inventors: Ru-Ling Liao, Jie Chen, Yan Ye, Jiancong Luo
  • Publication number: 20260332773
    Abstract: A video decoding method using a subblock temporal motion prediction for regular inter mode (sbAmvp mode). The method includes: receiving a bitstream comprising one or more syntax elements signaling coding unit (CU) level motion information associated with a CU, wherein the CU is encoded using regular inter mode; dividing the CU into a plurality of subblocks; and performing the sbAmvp mode on the plurality of subblocks.
    Type: Application
    Filed: July 2, 2026
    Publication date: October 22, 2026
    Inventors: Ru-ling LIAO, Jie CHEN, Yan YE, Xinwei LI
  • Publication number: 20260332785
    Abstract: The present disclosure provides a computer-implemented method for encoding or decoding video. The method includes encoding or decoding, in a plurality of picture parameter sets (PPS) associated with pictures of a coded layer video sequence (CLVS), corresponding first PPS flags indicating whether pictures are allowed to be partitioned into a plurality of tiles or slices. In a first PPS, a corresponding first PPS flag with a first value indicates a first picture of the CLVS is unpartitioned, and in a second PPS, another corresponding first PPS flag with a second value being different from the first value indicates that a second picture of the CLVS is allowed to be partitioned.
    Type: Application
    Filed: June 29, 2026
    Publication date: October 22, 2026
    Inventors: Jie CHEN, Yan YE, Ru-Ling LIAO
  • Patent number: 12771847
    Abstract: The present disclosure provides a video data processing method for cross-component sample adaptive offset (CCSAO). The method includes determining an index based on a vertical coordinate of a chroma sample within a picture; determining a luma sample based on the index; classifying the chroma sample based on a reconstructed value associated with the luma sample; determining an offset based on the classification; and adding the offset to a reconstructed value associated with the chroma sample.
    Type: Grant
    Filed: February 27, 2025
    Date of Patent: October 20, 2026
    Assignee: Alibaba (China) Co., Ltd.
    Inventors: Xinwei Li, Jie Chen, Ru-Ling Liao, Yan Ye
  • Publication number: 20260322998
    Abstract: A video processing method includes: determining whether an inter predictor correction is enabled for a coding block; and when the inter predictor correction is enabled for the coding block, performing the inter predictor correction by: obtaining a plurality of predicted samples from a top boundary and a left boundary of a predicted block corresponding to the coding block; obtaining a plurality of reconstructed samples from top neighboring reconstructed samples and left neighboring reconstructed samples of the coding block; and deriving a corrected predicted block based on the plurality of the predicted samples, the plurality of the reconstructed samples and the predicted block.
    Type: Application
    Filed: March 17, 2026
    Publication date: October 15, 2026
    Inventors: Xinwei LI, Jie CHEN, Ru-Ling LIAO, Yan YE
  • Publication number: 20260303792
    Abstract: The present disclosure provides a computer-implemented method for video processing. The method includes receiving a bitstream; and decoding the bitstream to form/generate/output a video sequence. The decoding includes decoding a flag indicating whether a subblock transform (SBT) intra mode is applied for a current coding unit (CU), wherein the current CU is coded in an intra prediction mode; in response to the flag indicating the SBT intra mode is applied, determining a sub-mode of the SBT intra mode; and decoding residuals of a sub-block based on the sub-mode.
    Type: Application
    Filed: March 10, 2026
    Publication date: October 1, 2026
    Inventors: Xinwei LI, Ru-ling LIAO, Jie CHEN, Yan YE
  • Publication number: 20260303817
    Abstract: A method for encoding video data includes: determining motion vector predictors (MVP) for a target block based on control point motion vectors (CPMV), in which a bilinear model is represented by the CPMVs; determining motion vector differences (MVD), in which each motion vector difference is based on a difference between the corresponding MVP and the CPMV for each control point; and setting the MVDs in a bitstream, in response to the bilinear model being used.
    Type: Application
    Filed: March 6, 2026
    Publication date: October 1, 2026
    Inventors: Jie CHEN, Ru-ling LIAO, Yan YE, Xinwei LI
  • Publication number: 20260301235
    Abstract: The present disclosure provides a computer-implemented method for video processing. The method includes receiving a video sequence; and encoding the video sequence by: determining a block size of a block; determining whether the block size is included in a first list; in response to the block size is not included in the first list, determining whether the block size is included in a second list; in response to the block size is included in the second list, selecting a neural network model for the block size and performing downsampling on the block based on the block size and the neural network model; and performing a neural network-based intra prediction (NNIP) on the block using the neural network model.
    Type: Application
    Filed: March 3, 2026
    Publication date: October 1, 2026
    Inventors: Zixiang ZHANG, Jie CHEN, Xinwei LI, Ru-ling LIAO, Yan YE
  • Publication number: 20260303818
    Abstract: A method of decoding a bitstream to output one or more pictures for a video stream includes: receiving a bitstream; and decoding, using coded information of the bitstream, one or more pictures. The decoding includes: determining a first motion vector predictor (MVP) and a second motion vector predictor (MVP) for a bi-predictive block coded in an advanced motion vector prediction (AMVP) mode, in which the first MVP is obtained from a first reference picture, and the second MVP is obtained from a second reference picture; and applying at least one of a decoder-side motion vector refinement (DMVR) process or a bilateral matching (BM) process based on a bilateral matching cost to refine at least one of the first MVP or the second MVP.
    Type: Application
    Filed: March 6, 2026
    Publication date: October 1, 2026
    Inventors: Ru-ling LIAO, Jie CHEN, Xinwei LI, Yan YE
  • Patent number: 12750520
    Abstract: Methods and apparatuses are provided for motion template-matching-based motion refinement. An exemplary method includes: dividing a target coding block into a plurality of subblocks; determining a first plurality of templates associated with the plurality of subblocks; determining a plurality of reference templates based on the first plurality of templates; performing motion compensation to the target coding block based on an affine merge candidate; and refining the motion compensation by matching the first plurality of templates and the plurality of reference templates.
    Type: Grant
    Filed: September 25, 2024
    Date of Patent: September 29, 2026
    Assignee: Alibaba (China) Co., Ltd.
    Inventors: Jie Chen, Ru-Ling Liao, Xinwei Li, Yan Ye
  • Patent number: 12750490
    Abstract: A video decoding method using a subblock temporal motion prediction for regular inter mode (sbAmvp mode). The method includes: receiving a bitstream comprising one or more syntax elements signaling coding unit (CU) level motion information associated with a CU, wherein the CU is encoded using regular inter mode; dividing the CU into a plurality of subblocks; and performing the sbAmvp mode on the plurality of subblocks. Performing the sbAmvp mode includes: deriving motion information for a subblock of the plurality of subblocks based on the signaled CU-level motion information.
    Type: Grant
    Filed: October 16, 2023
    Date of Patent: September 29, 2026
    Assignee: Alibaba Damo (Hangzhou) Technology Co., Ltd.
    Inventors: Ru-ling Liao, Jie Chen, Yan Ye, Xinwei Li
  • Publication number: 20260292237
    Abstract: The present disclosure provides computer-implemented methods for video processing. The method includes receiving a video sequence; and encoding the video sequence by determining whether a collocated block in a collocated picture of a current block has a block vector (BV); in response to the collocated block having the BV, determining the BV; determining a motion vector for Temporal Motion Vector Prediction (TMVP) for the current block based on the BV of the collocated block; and determining a reference index of the TMVP to be a reference index of the collocated picture.
    Type: Application
    Filed: March 3, 2026
    Publication date: September 24, 2026
    Inventors: Ru-ling LIAO, Jie CHEN, Yan YE, Xinwei LI
  • Publication number: 20260281304
    Abstract: A VVC-standard encoder and a VVC-standard decoder are provided, implementing derivation of a BCW index according to cost values based on template matching. A template matching cost can be calculated for each among a set of possible BCW weight values, and a BCW weight value yielding a lowest template matching cost among each template matching cost calculated can be selected as a BCW index for a bi-predicted merge candidate. Alternatively, a template matching cost can be calculated for each among a subset of possible BCW weight values based on an inherited BCW weight. Additionally, a merge candidate BCW index can be derived while adjusting template matching cost of an inherited BCW weight from a value calculated according to the VVC standard and ECM specifications, or while adjusting template matching cost of a BCW weight having equal weight from a value calculated according to the VVC standard and ECM specifications.
    Type: Application
    Filed: December 1, 2025
    Publication date: September 17, 2026
    Inventors: Ru-Ling Liao, Jie Chen, Yan Ye, Xinwei Li
  • Patent number: 12739423
    Abstract: Methods and apparatuses are provided for subblock-based temporal motion vector prediction (SbTMVP). An exemplary decoding method includes: decoding a target coding unit (CU) based on a SbTMVP mode, wherein the target CU is divided into a plurality of subblocks; determining a same reference picture index for the plurality of subblocks; selecting, based on the determined reference picture index, a reference picture from a list of reference pictures; generating a plurality of predicted subblocks based on the selected reference picture; and reconstructing the target CU based on the plurality of predicted subblocks.
    Type: Grant
    Filed: September 24, 2024
    Date of Patent: September 15, 2026
    Assignee: Alibaba (China) Co., Ltd.
    Inventors: Ru-ling Liao, Yan Ye, Jie Chen, Xinwei Li, Yeping Zheng
  • Publication number: 20260270398
    Abstract: An AVS3 and later-standard encoder and an AVS3 and later-standard decoder are provided, configuring one or more processors of a computing system to perform angular weighted prediction. The encoder and the decoder are configured to implement performing angular weighted prediction by constructing motion vector candidate lists including more MV candidates and additional types of MV candidates, and extending the candidate list length; by performing template matching based on reconstructed pixels surrounding the current block to reorder the MV candidates; and by performing motion vector refinement based on template matching to partitions of the current block.
    Type: Application
    Filed: February 27, 2026
    Publication date: September 10, 2026
    Inventors: Li Yu, Jiabao Zhu, Wanglin Lai, Hongbo Li, Yucheng Zhong, Jie Chen, Ru-ling Liao, Yan Ye
  • Patent number: 12726624
    Abstract: The present disclosure provides systems and methods for processing video content. The method can include: receiving data representing a first block and a second block in a picture, the data comprising a plurality of chroma samples associated with the first block and a plurality of luma samples associated with the second block; determining an average value of the plurality of luma samples associated with the second block; determining a chroma scaling factor for the first block based on the average value; and processing the plurality of chroma samples associated with the first block using the chroma scaling factor.
    Type: Grant
    Filed: August 7, 2024
    Date of Patent: September 1, 2026
    Assignee: ALIBABA GROUP HOLDING LIMITED
    Inventors: Yan Ye, Jie Chen, Ru-Ling Liao
  • Patent number: 12720108
    Abstract: A method for processing video includes receiving a bitstream; and decoding, using coded information of the bitstream, one or more pictures. The decoding includes performing overlapped block motion compensation (OBMC) on a block predicted with an intra mode.
    Type: Grant
    Filed: June 20, 2024
    Date of Patent: August 25, 2026
    Assignee: Alibaba (China) Co., Ltd.
    Inventors: Xinwei Li, Ru-ling Liao, Jie Chen, Yan Ye
  • Patent number: 12695902
    Abstract: Methods are provided for optical flow-based motion refinement. An exemplary method includes: receiving a bitstream; and decoding, using coded information of the bitstream, one or more pictures, wherein the decoding includes: determining whether a current block is coded by partitioning into multiple parts; and in response to the current block being partitioned into multiple parts that are inter predicted according to respective reference blocks, determining whether to apply a local illumination compensation (LIC) process to the multiple parts based on whether a coded block applies the LIC process.
    Type: Grant
    Filed: September 24, 2024
    Date of Patent: July 28, 2026
    Assignee: Alibaba (China) Co., Ltd.
    Inventors: Xinwei Li, Ru-ling Liao, Jie Chen, Yan Ye
  • Publication number: 20260197489
    Abstract: Methods and systems implement interpolation filters for motion prediction, and more specifically interpolation filters for template matching and decoder-side motion vector refinement (“DMVR”). A VVC and later standard encoder and a VVC and later standard decoder can configure one or more processors of a computing system to signal that at least one of a first filter derived by discrete cosine transform-based interpolation filter, a second filter derived by a cubic-based interpolation filter, and a third filter derived by a cubic-based interpolation filter are applied in a template matching-based mode, applied in DMVR search, or applied in both.
    Type: Application
    Filed: December 30, 2025
    Publication date: July 9, 2026
    Inventors: Zhenyu DAI, Ru-ling Liao, Yan Ye, Xinwei Li, Jie Chen
  • Publication number: 20260197438
    Abstract: Methods and systems implement application of chained motion vector prediction (“CMVP”). A VVC and later standard encoder and a VVC and later standard decoder, and/or an AVS3 and later-standard encoder and an AVS3 and later-standard decoder, can configure one or more processors of a computing system to apply CMVP in conjunction with Advanced Motion Vector Prediction (“AMVP”) mode while constructing spatially neighboring MVP candidates; apply CMVP in conjunction with Affine merge mode when inheriting Affine candidates; and apply CMVP in conjunction with subblock-based temporal motion vector prediction (“SbTMVP”) to obtain new motion shifts.
    Type: Application
    Filed: December 30, 2025
    Publication date: July 9, 2026
    Inventors: Chen Li, Ru-ling Liao, Jie Chen, Yan Ye