Sz Dji Technology Co., Ltd.

Tencent Technology (Shenzhen) Company Limited

Huawei Technologies Co., Limited

Tsinghua University

Weiran Li

Xiaozhen Zheng

Siwei Ma

Shanshe Wang

Suhong Wang

Chenchen Gu

Xinwei Gao

Tianliang Fu

Xunan Mao

Yun He

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.

Method and device for image motion compensation

A video processing method includes obtaining motion information of a left neighboring block of a current image block, and, where the left neighboring block satisfies a condition, determining, in a collocated frame of the current image block, a related block of a sub-block of the current image block using a motion vector of the left neighboring block as a motion offset, and determining a motion vector of the sub-block according to a motion vector of the related block. The preset condition includes a reference image of the left neighboring block being same as the collocated frame of the current image block. Determining the motion vector of the sub-block includes, where reference images of the related block and the sub-block are not specific reference images, determining the motion vector of the sub-block according to a scaled motion vector obtained by scaling the motion vector of the related block.

Method and device for obtaining motion vector of video image

A video encoding method includes determining a base motion vector list that includes a dual-prediction base motion vector group including a first base motion vector and a second base motion vector, determining two motion vector offsets according to a preset offset set, determining motion vectors of a current image block according to the first base motion vector, the second base motion vector, and the two motion vector offsets, and performing prediction on the current image block according to the motion vectors of the current image block.

Method and device for video image processing

A video image processing method includes dividing a current image block into a plurality of sub-blocks, in response to a target neighboring block of the current image block satisfying a preset condition, determining related blocks of the sub-blocks in a collocated frame of the current image block according to a motion vector of the target neighboring block, encoding or decoding the current image block according to motion vectors of the related blocks of the sub-blocks, determining a group of control point motion vectors in an affine transformation mode using one or more neighboring blocks of the current image block, and adding the group of control point motion vectors to a motion vector candidate list of the current image block.

A video decoding method includes obtaining a current video frame and determining a region of interest (ROI) of the current video frame. The method also includes decoding the ROI by using a first resolution, and decoding at least other regions of the current video frame than the ROI by using second resolutions, the first resolution being higher than the second resolution.

Video decoding method and apparatus, video encoding method and apparatus, storage medium, and electronic device

A video decoding method, a video encoding method, and related apparatuses. The method includes: obtaining a current video frame to be decoded, the current video frame being divided into a plurality of regions; determining a corresponding resolution for each region in the plurality of regions, to obtain a plurality of resolutions, the plurality of resolutions including at least two different resolutions; and decoding a video block in each region in the plurality of regions by using a corresponding resolution, the current video frame being divided into a plurality of video blocks. In this application, the technical problem of relatively large fluctuations in a PSNR caused by encoding and decoding of a video by using the same resolution in the related art is resolved.

Video encoding method, video decoding method, and related apparatuses

This application discloses a video encoding method and apparatus, a video decoding method and apparatus, an electronic device, and a computer-readable storage medium. The method includes: obtaining a current video frame, the current video frame being divided into a plurality of tile-divided Tile regions; determining a resolution corresponding to each Tile region in the plurality of Tile regions to obtain a plurality of resolutions, the plurality of resolutions including at least two different resolutions; and decoding the Tile region based on the resolution corresponding to the Tile region among the plurality of resolutions, to obtain a decoded video frame.

Video encoding method and apparatus, video decoding method and apparatus, electronic device and readable storage medium

A video encoding method including obtaining a motion vector candidate list of a current image block; determining a base motion vector according to motion vectors in the motion vector candidate list; in response to the base motion vector pointing to a short-term reference image, scaling a motion vector offset of the base motion vector using a scaling factor to obtain a scaled motion vector offset, and performing prediction for the current image block according to a motion vector determined by the scaled motion vector offset and the base motion vector; and in response to the base motion vector pointing to a long-term reference image, skipping scaling of the motion vector offset, and performing prediction for the current image block according to a motion vector determined by the motion vector offset that is not scaled and the base motion vector.

Disclosed is a video decoding method, including: obtaining a current video frame, the current video frame being partitioned into a plurality of regions; obtaining a syntax element carried in syntax data corresponding to each of the plurality of regions, the syntax element being used for indicating a resolution used to decode the region, and a plurality of resolutions used to decode the plurality of regions including at least two different resolutions; and decoding the each of the plurality of regions by using the resolution corresponding to the region. The plurality of resolutions are determined according to a transmission bandwidth of a video stream including the current video frame from a source to a destination, e.g., by comparing the transmission bandwidth with a preset bandwidth threshold.

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.

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.

A video decoding method is disclosed and performed by an electronic device, the method including: obtaining a first resolution used in decoding a current block and a second resolution used in decoding a reference block in a current video frame, the reference block being a reference block used for performing directional prediction on the current block in the current video frame; building a reconstruction block from the reference block; when the first resolution is greater than the second resolution, adjusting the reconstruction block of the reference block to the first resolution to obtain a first reconstruction block; and performing directional prediction on the current block according to the first reconstruction block and the current block.

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.

A video processing method is provided. In the method, at least one pair of decoded blocks to be reconstructed in a video frame is determined. Each pair of decoded blocks in the at least one pair of decoded blocks includes a first decoded block of a first resolution and a second decoded block of a second resolution. The first decoded block is adjacent to the second decoded block. The first resolution of the first decoded block is adjusted to a target resolution. The second resolution of the second decoded block is adjusted to the target resolution. A first edge pixel set in the first decoded block is determined. A second edge pixel set in the second decoded block is determined, the second edge pixel set being adjacent to the first edge pixel set. Further, the first edge pixel set and the second edge pixel set are filtered.

Video processing method and apparatus, storage medium, and electronic device

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.

Growing community of inventors

Shenzhen, China

Weiran Li