X
Xu Jizheng
Researcher at Microsoft
Publications - 457
Citations - 6157
Xu Jizheng is an academic researcher from Microsoft. The author has contributed to research in topics: Video processing & Motion vector. The author has an hindex of 33, co-authored 457 publications receiving 5071 citations.
Papers
More filters
Patent
Multi-hmvp for affine
TL;DR: In this article, a multi-HMVP for affine model for video processing is described, for a conversion between a current block of video and a bitstream representation of the current block, based on affine related information stored in at least one history motion vector prediction buffer of multiple HMVP buffers.
Patent
Usage of default and user-defined scaling matrices
TL;DR: In this article, a video processing method includes determining, for a conversion between a video block of a video and a coded representation of the video, factors of a scaling tool based on a coding mode of the encoded video block; and performing the conversion using the scaling tool.
Patent
High precision transform and quantization for image and video coding
TL;DR: In this article, a method of video processing includes determining, for a conversion between a video comprising a current block and a bitstream representation of the video, that the conversion comprises an application of a transform to the current block, and performing, based on the determining, the conversion, wherein a bit-shifting operation of a scaling process for transform coefficients associated with the transform is based on whether the block is coded with a block-based differential pulse code modulation (BDPCM) mode.
Patent
Regression-based motion vector field based sub-block motion vector derivation
TL;DR: In this article, the authors describe a method for video coding based on RMVF-based motion vector information, which includes deriving at least one motion model for a current video block, based on motion information of at least 1 non-adjacent spatial neighboring block or at least 2 temporal neighboring block.
Patent
Size restriction for intra-block copy virtual buffer
TL;DR: In this article, a method for video processing is described, which comprises: making a decision, for a conversion between a current video block of a video picture of video and a coded representation of the video.