Video coding method and device, video decoding method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of video processing, and discloses a video coding method and device, video decoding method and device, electronic equipment and a storage medium, relates to an artificial intelligence technology, and aims to perform video filtering by using a machine learning technology in artificial intelligence, so that blocks with relatively large gains can be screened out for filtering, and the filtering efficiency is improved. The method comprises: obtaining a reconstructed video frame from encoded data of the video frame, the video frame comprising at least one block; carrying out filtering processing on the reconstructed video frame, and obtaining a gain obtained after filtering processing of each pixel point in the reconstructed video frame; for each block in the at least one block, according to the gain distribution of each pixel point in each block, determining whether filtering processing needs to be performed on each block when the coded data is decoded; and sending coded data of the video frame, wherein the coded data comprises indication information of the block needing to be filtered.

Description

Technical field [0001] The present application relates to the field of video processing, and more particularly to a video coding, a decoding method, a device, an electronic device, and a storage medium. Background technique [0002] In recent years, with the development of deep learning technology, there have been many research attempts to replace partial modules in the traditional video coding frame or propose deep learning-based end-to-end coding framework, especially on loop filtering tools. Compared to conventional filtering tools can significantly improve coding performance. However, the use of deep learning loop filtering tools will increase the decoding complexity of the video decoding end, and the current processing method is to filter out the filter frame through the RDO (RateDistort Optimization, the rate distortion). CTU (Coding Tree Unit, coding tree unit), and filtering this part of the CTU on the video decoding end. Inventive content [0003] However, even if there...

AI Technical Summary

Problems solved by technology

However, the use of loop filtering tools based on deep learning will increase the decoding complexity of the video decoding end. The current processing method is to use RDO (Ratedistortion optimization, rate-distortion optimization) to filter out the gain in the filtered video frame. The CTU (Coding Tree Unit, coding tree unit), and filter this part of the CTU at the video decoding end

Images