Methods and equipment for decoding video and storage media

Abstract

The invention relates to a method, apparatus, and computer-readable, invariant storage medium for decoding video. The apparatus may include a processing circuit. The processing circuit is structured to decode first-order neural network update information in the bit stream encoded for first-order neural networks in a video decoder. First-order neural networks are configured with first-order pre-trained parameters. The first neural network update corresponds to the first block in the image to be recovered, and the first substitution parameter indicator corresponds to the first pre-trained parameter among the first pre-trained parameters. The processing circuit is structured to update the first neural network in the microdecoder based on the first substitution parameter. The processing circuit can decode the first block based on the first neural network updated with the first block.