Patents by Inventor Xiaozhen ZHENG
Xiaozhen ZHENG 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: 20240137559Abstract: A video processing method includes obtaining a first initial motion vector (MV) and a second initial MV. The first initial MV points to a first reference image, and the second initial MV points to a second reference image. The method further includes, in response to the first reference image and the second reference image being both short-term reference images, calculating a motion offset of a current image block based on gradients at sampling points pointed to by the first initial MV and the second initial MV, and calculating a predicted image block of the current image block based on the motion offset of the current image block.Type: ApplicationFiled: December 18, 2023Publication date: April 25, 2024Inventors: Xiaozhen ZHENG, Weiran LI
-
Patent number: 11949911Abstract: A video processing method includes obtaining motion information of a neighboring block of a current image block, dividing the current image block into a plurality of sub-blocks in response to the neighboring block satisfying a preset condition, determining, in a time-domain reference image of the current image block, related blocks of the plurality of sub-blocks according to a motion vector of the neighboring block, and performing prediction on the current image block according to motion vectors of the related blocks.Type: GrantFiled: May 23, 2022Date of Patent: April 2, 2024Assignee: SZ DJI TECHNOLOGY CO., LTD.Inventors: Xiaozhen Zheng, Suhong Wang, Shanshe Wang, Siwei Ma, Weiran Li
-
Patent number: 11949912Abstract: A video image processing method includes determining a related block of a current image block according to a motion vector of a target neighboring block, the current image block, and a collocated frame of the current image block, decoding the current image block according to a motion vector of the related block of the current image block, constructing motion vectors of part of control points of the current image block according to neighboring blocks of the part of the control points of the current image block, and adding the motion vectors of the part of the control points of the current image block to a motion vector candidate list of the current image block.Type: GrantFiled: June 20, 2022Date of Patent: April 2, 2024Assignee: SZ DJI TECHNOLOGY CO., LTD.Inventors: Xiaozhen Zheng, Tianliang Fu, Shanshe Wang, Siwei Ma, Weiran Li, Suhong Wang
-
Patent number: 11936847Abstract: A video processing method includes dividing a region of a current frame to obtain a plurality of image blocks, obtaining a historical motion information candidate list, and obtaining candidate historical motion information for the plurality of image blocks according to the historical motion information candidate list. The candidate historical motion information is a candidate in the historical motion information candidate list. The method further includes performing prediction for the plurality of image blocks according to the candidate historical motion information. A size of each of the plurality of image blocks is smaller than or equal to a preset size. The same historical motion information candidate list is used for the plurality of image blocks during the prediction. The historical motion information candidate list is not updated while the prediction is being performed for the plurality of image blocks.Type: GrantFiled: June 29, 2021Date of Patent: March 19, 2024Assignee: SZ DJI TECHNOLOGY CO., LTD.Inventors: Suhong Wang, Xiaozhen Zheng, Shanshe Wang, Siwei Ma
-
Patent number: 11871032Abstract: An image motion compensation method includes obtaining a first initial MV and a second initial MV of a current image block. The method further includes: if at least one of reference images pointed to by the first and second initial MVs is a long-term reference image, skipping scaling of the first and second initial MVs and performing motion compensation on the current image block based on the first and second initial MVs; and/or, if both the reference images pointed to by the first and second initial MVs are short-term reference images, determining scaling factors of the first and second initial MVs, scaling the first and second initial MVs based on the scaling factors, and performing motion compensation on the current image block based on the first and second initial MVs after being scaled.Type: GrantFiled: July 5, 2022Date of Patent: January 9, 2024Assignee: SZ DJI TECHNOLOGY CO., LTD.Inventors: Xiaozhen Zheng, Weiran Li
-
Patent number: 11871004Abstract: A video image processing method includes binarizing a chrominance prediction mode of the image block of a to-be-encoded/decoded image to obtain a bit string, the bit string including two adjacent bits, the to-be-encoded/decoded image being permitted to use a CCLM and/or a regular intra-frame chrominance prediction mode, and the CCLM including a first mode, a second mode, and a third mode, and using mutually independent probability models to encode/decode a first bit and a second bit. The first bit of the adjacent bits indicates whether the CCLM is used, the second bit indicates whether to use the first mode of the CCLM when the first bit indicates to use the CCLM, the third bit indicates whether the second mode or the third mode of the CCLM is used when the second bit indicates that the first mode of the CCLM is not used.Type: GrantFiled: December 23, 2021Date of Patent: January 9, 2024Assignee: SZ DJI TECHNOLOGY CO., LTD.Inventors: Siwei Ma, Jiaqi Zhang, Xiaozhen Zheng, Shanshe Wang
-
Publication number: 20230421807Abstract: A method for processing an intra prediction mode includes: determining whether an intra prediction mode of each neighboring block in multiple neighboring blocks of a current block is applicable to the current block; and obtaining multiple mapped intra prediction modes of the current block according to a result of the determining, if it is determined that an intra prediction mode of a neighboring block is applicable to the current block, setting the intra prediction mode of the neighboring block as a mapped intra prediction mode of the current block, and if it is determined that the intra prediction mode of the neighboring block is not applicable to the current block, setting a specific intra prediction mode as the mapped intra prediction mode of the current block.Type: ApplicationFiled: September 1, 2023Publication date: December 28, 2023Inventors: Yongbing Lin, Xiaozhen Zheng
-
Publication number: 20230345036Abstract: A video image processing method including determining a current image block, constructing a motion information candidate list for the current image block, in response to a size of the current image block meeting a preset condition, turning off a temporal motion vector prediction (TMVP) operation so that a temporal candidate motion vector of the current image block is not determined according to the TMVP operation, and encoding the current image block. The TMVP operation includes determining a relevant block of the current image block in a temporal neighboring image, and determining the temporal candidate motion vector of the current image block according to a motion vector of the relevant block.Type: ApplicationFiled: June 26, 2023Publication date: October 26, 2023Inventors: Xiaozhen ZHENG, Suhong WANG, Shanshe WANG, Siwei MA
-
Patent number: 11770556Abstract: A method for processing an intra prediction mode includes: determining whether an intra prediction mode of each neighboring block in multiple neighboring blocks of a current block is applicable to the current block; and obtaining multiple mapped intra prediction modes of the current block according to a result of the determining, if it is determined that an intra prediction mode of a neighboring block is applicable to the current block, setting the intra prediction mode of the neighboring block as a mapped intra prediction mode of the current block, and if it is determined that the intra prediction mode of the neighboring block is not applicable to the current block, setting a specific intra prediction mode as the mapped intra prediction mode of the current block.Type: GrantFiled: December 14, 2020Date of Patent: September 26, 2023Assignee: Huawei Technologies Co., Ltd.Inventors: Yongbing Lin, Xiaozhen Zheng
-
Patent number: 11743482Abstract: A video image processing method includes determining a current image block; in response to a size of the current image block not meeting a first preset condition, skipping an advanced/alternative temporal motion vector prediction (ATMVP) operation so that a temporal candidate motion vector of the current image block is not determined according to the ATMVP operation; and encoding the current image block. The ATMVP operation includes determining a relevant block of the current image block in a temporal neighboring image; dividing the current image block into a plurality of sub-blocks; for each of the sub-blocks, determining a corresponding relevant sub-block in the relevant block; and determining temporal candidate motion vectors of the sub-blocks of the current image block according to motion vectors of the relevant sub-blocks corresponding to the sub-blocks.Type: GrantFiled: November 15, 2021Date of Patent: August 29, 2023Assignee: SZ DJI TECHNOLOGY CO., LTD.Inventors: Suhong Wang, Xiaozhen Zheng, Shanshe Wang, Siwei Ma
-
Publication number: 20230262221Abstract: A method and device for coding and decoding are disclosed. The method includes: dividing a picture to be encoded into several slices, each containing macroblocks continuous in a designated scanning sequence in the picture; dividing slices in the picture into one or more slice sets according to attribute information of the slices, each slice set containing one or more slices; and encoding the slices in the slice sets according to slice and slice set division information to get a coded bit stream of the picture. The decoding method includes: obtaining slice and slice set division information from a bit stream to be decoded and decoding the bit stream according to the obtained slice and slice set division information. The invention improves the performance of video transmission effectively and realizes region based coding. The implementation of coding and decoding is simple and the complexity of coding and decoding systems is reduced.Type: ApplicationFiled: April 18, 2023Publication date: August 17, 2023Applicants: HUAWEI TECHNOLOGIES CO., LTD., TSINGHUA UNIVERSITYInventors: Xiaozhen Zheng, Zhen Mao, Ziyuan Wang, Yun He, Xiaozhong Xu, Jianhua Zheng
-
Patent number: 11689736Abstract: A video image processing method including determining a current image block, in response to a size of the current image block meeting a preset condition, skipping a temporal motion vector prediction (TMVP) operation so that a temporal candidate motion vector of the current image block is not determined according to the TMVP operation, and encoding the current image block. The TMVP operation includes determining a relevant block of the current image block in a temporal neighboring image, and determining the temporal candidate motion vector of the current image block according to a motion vector of the relevant block.Type: GrantFiled: December 20, 2021Date of Patent: June 27, 2023Assignee: SZ DJI TECHNOLOGY CO., LTD.Inventors: Xiaozhen Zheng, Suhong Wang, Shanshe Wang, Siwei Ma
-
Patent number: 11659184Abstract: A method and device for coding and decoding are disclosed. The method includes: dividing a picture to be encoded into several slices, each containing macroblocks continuous in a designated scanning sequence in the picture; dividing slices in the picture into one or more slice sets according to attribute information of the slices, each slice set containing one or more slices; and encoding the slices in the slice sets according to slice and slice set division information to get a coded bit stream of the picture. The decoding method includes: obtaining slice and slice set division information from a bit stream to be decoded and decoding the bit stream according to the obtained slice and slice set division information. The invention improves the performance of video transmission effectively and realizes region based coding. The implementation of coding and decoding is simple and the complexity of coding and decoding systems is reduced.Type: GrantFiled: February 1, 2021Date of Patent: May 23, 2023Assignees: HUAWEI TECHNOLOGIES CO., LTD., TSINGHUA UNIVERSITYInventors: Xiaozhen Zheng, Zhen Mao, Ziyuan Wang, Yun He, Xiaozhong Xu, Jianhua Zheng
-
Publication number: 20230120657Abstract: A video encoding method includes encoding images of an image sequence to generate a bitstream of the image sequence. Different identifiers are used for two chrominance components of one image in a syntax element of an image level in the bitstream to indicate whether the corresponding chrominance components are filtered by adaptive loop filtering (ALF).Type: ApplicationFiled: September 30, 2022Publication date: April 20, 2023Inventors: Siwei MA, Xuewei MENG, Shanshe WANG, Xiaozhen ZHENG
-
Publication number: 20220353527Abstract: An image motion compensation method includes obtaining a first initial MV and a second initial MV of a current image block. The method further includes: if at least one of reference images pointed to by the first and second initial MVs is a long-term reference image, skipping scaling of the first and second initial MVs and performing motion compensation on the current image block based on the first and second initial MVs; and/or, if both the reference images pointed to by the first and second initial MVs are short-term reference images, determining scaling factors of the first and second initial MVs, scaling the first and second initial MVs based on the scaling factors, and performing motion compensation on the current image block based on the first and second initial MVs after being scaled.Type: ApplicationFiled: July 5, 2022Publication date: November 3, 2022Inventors: Xiaozhen ZHENG, Weiran LI
-
Patent number: 11490120Abstract: A video processing method includes dividing a coding tree unit into one or more coding units using a quadtree plus binary tree division method, determining a specific neighboring image block of a coding unit having a reference image same as a co-located reference image of the coding unit, determining a related reference block of the coding unit in the co-located reference image according to a motion vector of the specific neighboring image block, dividing the related reference block into several related reference sub-blocks, and performing prediction for the coding unit according to scaled or unscaled motion vector of the related reference sub-block depending on whether the motion vector of the related sub-block points to a short-term or a long-term reference image.Type: GrantFiled: April 1, 2021Date of Patent: November 1, 2022Assignee: SZ DJI TECHNOLOGY CO., LTD.Inventors: Xiaozhen Zheng, Weiran Li
-
Patent number: 11490118Abstract: A video processing method includes dividing a coding tree unit into one or more coding units using a quadtree plus binary tree division method, dividing a coding unit into one or more sub-blocks, determining a specific neighboring image block of the coding unit having a reference image same as a co-located reference image of the coding unit, determining a related reference block of the coding unit in the co-located reference image according to a motion vector of the specific neighboring image block, dividing the related reference block into several related reference sub-blocks, determining a scaling factor of a motion vector of the related reference sub-block in different manners according to whether that motion vector points to a short-term reference image or a long-term reference image, scaling that motion vector using the scaling factor, and performing prediction for the coding unit according to the scaled motion vector.Type: GrantFiled: September 30, 2020Date of Patent: November 1, 2022Assignee: SZ DJI TECHNOLOGY CO., LTD.Inventors: Xiaozhen Zheng, Weiran Li
-
Publication number: 20220345699Abstract: An in-loop filtering method includes determining a target filter for a chrominance component of a current block of an image from a plurality of cross-component ALF filters, determining target filter coefficients for the chrominance component according to the chrominance component after ALF and a luminance component of the current block without ALF, filtering the chrominance component after ALF according to the target filter and the target filter coefficients, determining a filtered chrominance component of the current block according to the chrominance component after being filtered with the target filter coefficients and the chrominance component after the ALF, encoding according to the filtered chrominance component of the current block, and encoding a total number of the plurality of cross-component ALF filters as a syntax element. A stream of the image includes only one syntax element for indicating the total number of the plurality of cross-component ALF filters.Type: ApplicationFiled: June 29, 2022Publication date: October 27, 2022Inventors: Siwei MA, Xuewei MENG, Xiaozhen ZHENG, Shanshe WANG
-
Publication number: 20220321907Abstract: A video image processing method includes, in response to a specific neighboring block of a current image block satisfying a preset condition, determining a collocated block of the current image block according to a motion vector of the specific neighboring block, determining a specific candidate from a motion vector candidate list of the current image block according to the collocated block of the current image block for using in prediction for the current image block, scanning neighboring blocks of the current image block and determining a control point motion vector group of each of one or more neighboring blocks that use an affine transformation mode for prediction, and adding the control point motion vector group of each of the determined one or more neighboring blocks into the motion vector candidate list of the current image block as a candidate.Type: ApplicationFiled: June 20, 2022Publication date: October 6, 2022Inventors: Xiaozhen ZHENG, Tianliang FU, Shanshe WANG, Siwei MA, Weiran LI, Suhong WANG
-
Publication number: 20220286706Abstract: A video processing method includes obtaining motion information of a neighboring block of a current image block, dividing the current image block into a plurality of sub-blocks in response to the neighboring block satisfying a preset condition, determining, in a time-domain reference image of the current image block, related blocks of the plurality of sub-blocks according to a motion vector of the neighboring block, and performing prediction on the current image block according to motion vectors of the related blocks.Type: ApplicationFiled: May 23, 2022Publication date: September 8, 2022Inventors: Xiaozhen ZHENG, Suhong WANG, Shanshe WANG, Siwei MA, Weiran LI