Bilateral-circulation convolution network-based video super-resolution method and system

Abstract

The invention discloses a bilateral-circulation convolution network-based video super-resolution method. The method comprises the steps as follows: establishing bilateral-circulation networks, comprising a forward circulation sub-network and a backward circulation sub-network according to time sequence, wherein each circulation sub-network comprises an input sequence layer, two implication sequence layers and an output sequence layer from the bottom to the top, and each sequence layer comprises a plurality of states corresponding to video frames in different moments; connecting these states by using three convolution operations, comprising a feed-forward convolution, a cyclic convolution and a condition convolution so as to obtain a bilateral-circulation convolution network; transmitting a trained video in the established bilateral-circulation convolution network, and using a stochastic gradient descent algorithm to minimize mean square error between a predicated high resolution video and an actual high resolution video so as to iteratively optimize the weight of the network, and obtain the final bilateral-circulation convolution network; and inputting low-resolution video sequence to be processed in a final bilateral-circulation convolution network mode to obtain a corresponding super-resolution result.

Description

technical field [0001] The invention relates to the fields of computer vision and machine learning, in particular to a video super-resolution method and system based on a bidirectional circular convolution network. Background technique [0002] With the emergence of a large number of high-definition playback devices in recent years, how to convert low-resolution video to high-resolution video that is more suitable for playback, that is, super-resolution technology, has gradually become a hot research issue in the field of computer vision. [0003] The current super-resolution work can be roughly divided into two categories: 1) single-image super-resolution, which assumes that all video frames are independent of each other, and then performs super-resolution on each video frame independently. This method ignores a very important feature in video sequences, that is, the temporal dependence between video frames. 2) Multi-frame super-resolution, this method takes into account t...

AI Technical Summary

Problems solved by technology

[0004] However, in practical applications, this modeling of temporal dependencies usually requires high computational costs, which largely limits the application range of multi-frame super-resolution techniques.

Images