Video-oriented super-resolution method and device, equipment and storage medium

Abstract

The embodiment of the invention provides a video-oriented super-resolution method and device, equipment and a storage medium. The video-oriented super-resolution method comprises the following steps:extracting a super-image based on continuous frame images in an original video; inputting the super-image vector corresponding to the super-image into a residual convolutional neural network to obtainan output result of the residual convolutional neural network; and inputting an output result of the residual convolutional neural network into a spatial upsampling network to obtain a super-resolution video frame, the super-resolution video of the original video comprising a plurality of video frames. According to the method provided by the embodiment of the invention, the time domain information in the original video is reserved on the basis of the super-image formed by the continuous frame images, and the residual convolutional neural network and the spatial sampling network are used for modeling the original video, so that the video super-resolution effect can be greatly improved under the calculation complexity of the same magnitude as that of the image super-resolution network.

Description

technical field [0001] The present invention relates to the technical field of video processing, in particular to a video-oriented super-resolution method, device, equipment and storage medium. Background technique [0002] With the rise of the mobile Internet, the way users store and forward information gradually transitions from text and pictures to video. However, video transmission requires high network bandwidth, and video storage also requires increased hard disk space. Video super-resolution technology can convert low-resolution video into high-resolution video. Video services can transmit and store lower-resolution videos, and use super-resolution technology to present high-resolution videos for users when playing, saving bandwidth and storage space while providing users with high-quality video viewing experience. In the existing super-resolution technology, the image super-resolution method is used to super-resolution the video frame by frame, the super-resolution...

AI Technical Summary

Problems solved by technology

In the existing super-resolution technology, the image super-resolution method is used to super-resolution the video frame by frame, the super-resolution effect is poor, and the motion blur in the video cannot be dealt with; The super-resolution method has a large amount of calculation, and due to the dependence on optical flow pre-training, the error in the pre-training will be propagated to the super-resolution task, resulting in the degradation of the super-resolution effect

Images