Abstract: The present disclosure provides methods for performing training and executing of a multi-density neural network in video processing. An exemplary method comprises: receiving a video stream comprising a plurality of pictures; processing the plurality of pictures using a first branch of a first block in the neural network, wherein the neural network is configured to reduce blocking artifacts in video compression of the video stream and the first branch comprises one or more residual blocks; and processing the plurality of pictures using a second branch of the first block in the neural network, wherein the second branch comprises a down-sampling processing, an up-sampling processing, and one or more residual blocks.

Abstract: This application discloses an encoding method, a decoding method, and a device. The encoding method includes: determining an index of an intra prediction mode syntax element value set of a current picture block; performing, by using a neural network, probability estimation on input data that represents a feature of the current picture block, to obtain probability distribution of a plurality of candidate intra prediction mode syntax element value sets, where the probability distribution represents respective probability values of the plurality of candidate intra prediction mode syntax element value sets; and performing entropy encoding on a probability value related to the index of the intra prediction mode syntax element value set of the current picture block based on the probability distribution of the plurality of candidate intra prediction mode syntax element value sets, to obtain a bitstream.