Tencent America LLC

Zeqiang Li

Shan Liu

Wei Jiang

Xiaozhong Xu

Wei W Wang

Byeongdoo Choi

Stephan Wenger

Wei Wang

A method, computer program, and computer system is provided for video encoding and decoding. Video data including a current picture is received. A virtual reference frame is generated for the current picture based on hierarchical level associated with the current picture and a nearest decoded picture. The video data is decoded based on the generated reference frame.

Utilizing hierarchical structure for neural network based tools in video coding

Video coding using neural network based inter-frame prediction is performed by generating a current reference frame by generating intermediate flows based on two input frames, performing backward warping of the input frames to generate reconstruction frames, and generating a fusion map and a residual map based on the input frames, the intermediate flows and the reconstruction frames. The video coding method further includes outputting an enhanced frame or a virtual reference picture by generating a feature map with different levels, based on the current reference frame, a first reference frame and a second reference frame, generating a predicted frame based on aligned features from the generated feature map by refining the current reference frame, the first reference frame, and the second reference frame, generating a final residual based on the predicted frame, and computing the enhanced frame as an output by adding the final residual to the current reference frame.

Techniques for deep neural network based inter- frame prediction in video coding

There is included a method and apparatus comprising computer code configured to cause a processor or processors to perform obtaining a video bitstream, coding the video bitstream at least partly by a neural network, determining topology information and parameters of the neural network, signaling the determined topology information and the parameters of the neural network in a plurality of syntax elements associated with the coded video bitstream.

Techniques for signaling neural network topology and parameters in the coded video stream

A method and apparatus for video coding comprising computer code configured to cause at least one processor to perform obtaining an input video stream, generating a coded video bitstream based on the input video stream using a neural network, the coded video bitstream including a plurality of supplemental enhancement information (SEI) messages and blocks, determining a plurality of pieces of neural network topology information associated with the neural network, and signaling the determined plurality of pieces of neural network topology information in a plurality of syntax elements associated with the coded video bitstream.

Techniques for signaling neural network topology, parameters, and processing information in video stream

A method, apparatus and storage medium for performing video coding are provided. The method includes obtaining a plurality of image frames in a video sequence; determining a feature map for each of the plurality of image frames and determining an offset map based on the feature map; determining an aligned feature map by performing a temporal deformable convolution (TDC) on the feature map and the offset map; and generating a plurality of aligned frames based on the aligned feature map.

Deep loop filter by temporal deformable convolution

A method, computer program, and computer system is provided for video encoding and decoding. Video data including one or more frames is received. One or more quantization parameters associated with the received video data are determined for frame generation or enhancement of a target frame from among the one or more frames. The video data is decoded based on the determined quantization parameters.

Multi-model selection for neural network based tools in video coding

A method of performing inter-picture prediction of a current picture of a video sequence is performed by at least one processor and includes determining whether the current picture uses a virtual reference picture, and based on the current picture being determined to use the virtual reference picture, generating, for the current picture, the virtual reference picture from neighboring reference pictures that are nearest neighbors to the virtual reference picture, storing the generated virtual reference picture in a decoded picture buffer, and adding the generated virtual reference picture to an active reference picture list. The method further includes performing the inter-picture prediction of the current picture, based on the active reference picture list to which the virtual reference picture is added.

Growing community of inventors

Palo Alto, CA, United States of America

Zeqiang Li