Patents by Inventor Jie Zhao

Jie Zhao 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).

  • Publication number: 20240430425
    Abstract: According to the disclosure of this document, it is possible to derive a residual sample by applying an adaptive color transform (ACT) to a current block on the basis of ACT-related information, and at this time, the residual sample is clipped and derived on the basis of a clipping range, wherein the clipping range is determined on the basis of a bit depth.
    Type: Application
    Filed: September 11, 2024
    Publication date: December 26, 2024
    Inventors: Jie ZHAO, Seunghwan KIM
  • Patent number: 12177422
    Abstract: A video decoding method performed by a video decoding apparatus according to the present document may comprise the steps of: parsing a prediction weighted table syntax from a bitstream; parsing number information about weighted reference pictures in a reference picture list from the prediction weighted table syntax; deriving a weighting factor-related flag about the reference picture list on the basis of the number information; performing weighted prediction on a current block on the basis of the weighting factor-related flag so as to derive prediction samples of the current block; generating residual samples on the basis of residual information obtained from the bitstream; and reconstructing a current picture on the basis of the prediction samples and the residual samples, wherein the prediction weighted table syntax is parsed from a picture header of the bitstream.
    Type: Grant
    Filed: June 28, 2023
    Date of Patent: December 24, 2024
    Assignee: LG ELECTRONICS INC.
    Inventors: Seethal Paluri, Hendry Hendry, Seunghwan Kim, Jie Zhao
  • Patent number: 12177485
    Abstract: According to the disclosure of the present document, an escape value may be effectively binarized on the basis of a maximum value of an escape value, which may be inferred by a quantization parameter in a palette mode. Accordingly, in a palette mode, the length of a bin may be adjusted or the number bits may be saved, according to a maximum value of an escape value, whereby coding efficiency may be improved.
    Type: Grant
    Filed: August 31, 2020
    Date of Patent: December 24, 2024
    Assignee: LG ELECTRONIC, INC.
    Inventors: Sunmi Yoo, Junghak Nam, Seunghwan Kim, Jie Zhao
  • Publication number: 20240422339
    Abstract: According to the disclosure of the present documents, a quantization parameter used in a scaling process of a quantized escape value in a palette mode may be derived on the basis of minimum quantization parameter information relating to a transform skip mode. Accordingly, the amount of data required to be signaled for video/image coding can be reduced and escape coding in a palette mode can be effectively performed.
    Type: Application
    Filed: August 26, 2024
    Publication date: December 19, 2024
    Inventors: Jie ZHAO, Seethal PALURI, Seunghwan KIM
  • Patent number: 12170777
    Abstract: A video decoding method performed by a decoding device according to the present document is characterized by comprising: a step for acquiring information for a chroma quantization parameter (QP) offset for the current picture; and a step for acquiring chroma QP offset index information for a current chroma block in the current picture, wherein the information for the chroma QP offset includes chroma QP offset list length information, information for a chroma QP offset list is acquired on the basis of the chroma QP offset list length information, and the chroma QP offset index information is acquired on the basis of the chroma QP offset list length information.
    Type: Grant
    Filed: November 4, 2020
    Date of Patent: December 17, 2024
    Assignee: LG ELECTRONICS INC.
    Inventors: Hendry Hendry, Jie Zhao, Seunghwan Kim
  • Publication number: 20240414354
    Abstract: According to one embodiment of the present disclosure, a method by which a decoding device decodes an image is provided. The method comprises the steps of: acquiring image information from a bit-stream; determining whether at least one from among a template-based inter mode derivation (TIMD) mode and decoder-side intra mode derivation (DIMD) mode is applied to the current block; generating a prediction sample of the current block on the basis of the at least one from among the TIMD mode and DIMD mode; and generating a reconstructed sample of the current block on the basis of the prediction sample of the current block, wherein the TIMD mode is derived from a template of the current block and the DIMD mode is derived on the basis of the gradient of adjacent reference samples of the current block.
    Type: Application
    Filed: September 30, 2022
    Publication date: December 12, 2024
    Inventors: Seunghwan KIM, Jie ZHAO, Seethal PALURI
  • Publication number: 20240414374
    Abstract: According to the disclosure of the present document, by configuring a primary transform to include a non-separable transform, higher encoding efficiency may be expected compared to the existing primary transform including only a separable transform. Also, by efficiently signaling information related to a primary transform including a separable transform and a non-separable transform, the effect of reducing the number of bits and improving coding performance may be expected. In addition, by efficiently applying a primary transform and a secondary transform, computational complexity and power consumption may be reduced, and latency required for additionally generated transform coefficient processing may be minimized.
    Type: Application
    Filed: October 20, 2022
    Publication date: December 12, 2024
    Inventors: Jungah CHOI, Seunghwan KIM, Moonmo KOO, Jie ZHAO, Jaehyun LIM, Jangwon CHOI
  • Publication number: 20240414325
    Abstract: According to the disclosure of this document, it is possible to signal information related to a chroma quantization parameter offset through a palette coding syntax, and to efficiently parse and signal index information for a chroma quantization parameter offset list on the basis of information about the number of entries in the chroma quantization parameter offset list. Accordingly, bits that need to be signaled for video/image coding can be reduced, and coding efficiency can be improved.
    Type: Application
    Filed: August 22, 2024
    Publication date: December 12, 2024
    Inventors: Hendry Hendry, Seunghwan Kim, Jie Zhao
  • Publication number: 20240411016
    Abstract: This method comprises: pre-processing (312) SAR data of the geographical region to determine a plurality of SAR images (2), said region being subdivided into a plurality of adjacent cells; defining (314) an urban mask (4) of said region, said urban mask providing, for each cell, a likelihood that said cell is an urban area; applying (316), on the plurality of SAR images, a deep learning classification algorithm, to compute, for each cell of said region, a class (6) indicative that the corresponding cell is either a flooded urban area, a flooded rural area, or a non-flooded area, the deep learning classification algorithm being structured as a fully convolutional neural network (16) and comprising dynamic parameters and static parameters, the values of the dynamic parameters being computed from the urban mask and the value of the static parameter being computed during a training stage.
    Type: Application
    Filed: December 1, 2022
    Publication date: December 12, 2024
    Inventors: Jie ZHAO, Yu LI, Marco CHINI
  • Publication number: 20240414360
    Abstract: According to the disclosure of the present document, a residual sample can be derived by applying adaptive color transform (ACT) with respect to a current block on the basis of ACT-associated information, wherein the residual sample is derived by being clipped on the basis of a clipping boundary, wherein the clipping boundary is determined on the basis of a bit depth.
    Type: Application
    Filed: August 21, 2024
    Publication date: December 12, 2024
    Inventors: Jie ZHAO, Seunghwan KIM
  • Patent number: 12167002
    Abstract: According to the disclosure of the present document, the resources necessary for an LMCS process may be reduced by limiting the range that an LMCS APS occupies in all APSs. Thus, the degree of complexity in LMCS may be reduced, and video/image coding efficiency may be increased.
    Type: Grant
    Filed: June 13, 2023
    Date of Patent: December 10, 2024
    Assignee: LG ELECTRONICS INC.
    Inventors: Jie Zhao, Seunghwan Kim
  • Patent number: 12167024
    Abstract: Systems and methods for performing motion vector prediction for video coding are disclosed. A motion vector predictor is determined based at least in part on motion information associated with a selected motion vector predictor origin and offset values corresponding to a selected sampling point. The sampling point is specified according to a set of direction and distance on a sampling map for the motion vector predictor origin.
    Type: Grant
    Filed: December 20, 2021
    Date of Patent: December 10, 2024
    Assignee: SHARP KABUSHIKI KAISHA
    Inventors: Byeongdoo Choi, Kiran Mukesh Misra, Jie Zhao, Philip Cowan, Weijia Zhu, Sachin G. Deshpande, Frank Bossen, Christopher Andrew Segall
  • Publication number: 20240406419
    Abstract: According to the disclosure of the present document, it is possible to derive a residual sample by applying an adaptive color transform (ACT) to a current block on the basis of ACT related information, and at this time, the residual sample is derived through clipping on the basis of a clipping range, and the clipping range is determined on the basis of the bit depth.
    Type: Application
    Filed: August 14, 2024
    Publication date: December 5, 2024
    Inventors: Jie ZHAO, Seunghwan KIM
  • Publication number: 20240406396
    Abstract: An image encoding/decoding method and apparatus are provided. The image decoding method performed by the image decoding apparatus, according to the present disclosure, may comprise the steps of: determining whether a color space transformation is applied to residual samples of a current block; determining quantization parameter of the current block on the basis of whether the color space transformation is applied; and determining a transformation coefficient of the current block on the basis of the quantization parameter. The step of determining the quantization parameter may be performed by limiting the range of an effective value of the quantization parameter such that a value of the quantization parameter has a value less than or equal to a predetermined upper value and greater than or equal to a predetermined lower value.
    Type: Application
    Filed: June 6, 2024
    Publication date: December 5, 2024
    Inventors: Jie ZHAO, Seung Hwan KIM, Hendry HENDRY, Seethal PALURI
  • Publication number: 20240397048
    Abstract: An image decoding method performed by a decoding device according to the present document comprises the steps of: obtaining CU chroma QP offset-related information for a current chroma block on the basis of the size and tree type of the current chroma block; deriving a chroma QP for the current chroma block on the basis of the CU chroma QP offset-related information; deriving residual samples for the current chroma block on the basis of the chroma QP; and generating a reconstructed picture on the basis of the residual samples, wherein the CU chroma QP offset-related information includes a CU chroma QP offset flag and a CU chroma QP offset index for the current chroma block.
    Type: Application
    Filed: August 1, 2024
    Publication date: November 28, 2024
    Inventors: Jie ZHAO, Seunghwan KIM, Seethal PALURI
  • Patent number: 12155816
    Abstract: An image encoding/decoding method and apparatus for signaling decoded picture buffer (DPB) related information and profile tier level (PTL) related information and a method of transmitting a bitstream are provided. The image decoding method according to the present disclosure may comprise obtaining first information indicating the number of one or more decoded picture buffer (DPB) parameter syntax structures in a video parameter set (VPS), obtaining the one or more DPB parameter syntax structures from the VPS based on the first information, obtaining second information between one or more multi-layer output layer sets (OLSs) and the one or more DPB parameter syntax structures from the VPS based on the first information, selecting a DPB parameter syntax structure that applies to a current OLS based on the second information, and processing the current OLS based on the selected DPB parameter syntax structure.
    Type: Grant
    Filed: March 26, 2021
    Date of Patent: November 26, 2024
    Assignee: LG ELECTRONICS INC.
    Inventors: Hendry Hendry, Seung Hwan Kim, Seethal Paluri, Jie Zhao
  • Publication number: 20240388715
    Abstract: According to the present disclosure, ALF parameters and/or LMCS parameters can be hierarchically signaled, which enables a reduction in the amount of data to be signaled for video/image coding and an increase in the coding efficiency.
    Type: Application
    Filed: July 29, 2024
    Publication date: November 21, 2024
    Inventors: Seethal PALURI, Seunghwan KIM, Jie ZHAO
  • Publication number: 20240388737
    Abstract: According to the disclosure of the present document, scaling list data delivered in an adaptation parameter set (APS) may be signaled through a hierarchical structure, and the amount of data that needs to be signaled for video/image coding may be reduced and implementation may be facilitated by placing limits on the scaling list data delivered in the APS.
    Type: Application
    Filed: July 26, 2024
    Publication date: November 21, 2024
    Inventors: Seethal PALURI, Seunghwan KIM, Jie ZHAO
  • Patent number: 12149727
    Abstract: A video decoding method performed by a video decoding apparatus, according to the present document, comprises the steps of: parsing a flag for weighted prediction from a bitstream; parsing a prediction weighted table syntax from the bitstream on the basis of the flag; generating prediction samples by performing weighted prediction on a current block within a current picture on the basis of the prediction weighted table syntax; and generating reconstructed samples for the current block on the basis of the prediction samples, wherein the prediction weighted table syntax may be parsed from a picture header or slice header of the bitstream on the basis of a value of the flag.
    Type: Grant
    Filed: June 9, 2023
    Date of Patent: November 19, 2024
    Assignee: LG ELECTRONICS INC.
    Inventors: Seethal Paluri, Hendry Hendry, Jie Zhao, Seunghwan Kim
  • Publication number: 20240380891
    Abstract: According to the disclosure of the present document, it is possible for various LMCS application cases to apply an LMCS procedure to a block having a dual tree structure. In addition, the coding predormance of the block can be improved. According to the disclosure of the present document, resources required for the LMCS procedure can be reduced. Therefore, the complexity of the LMCS can be reduced and the video/image coding efficiency can be increased.
    Type: Application
    Filed: July 24, 2024
    Publication date: November 14, 2024
    Inventors: Jie ZHAO, Seunghwan KIM