Video processing method, video restoration method, video processing device, video restoration device and electronic equipment

Abstract

The invention provides a video processing method and device, a video restoration method and device and electronic equipment, and relates to the technical field of deep learning. The method comprises the steps: obtaining an original video; adjusting the quality influence parameter of the original video to obtain a target video corresponding to the original video, the video quality of the target video being lower than the video quality of the original video; wherein the quality influence parameters comprise at least two of the following parameters: a noise parameter, a brightness parameter and a definition parameter; constructing a video training set based on the original video and the target video; wherein the corresponding relation between the target video and the original video is stored in the video training set, the video training set is used for training the video restoration model, and the trained video restoration model is used for restoring the video. According to the invention, the video training set for training the neural network can be obtained, so that the problem that video restoration work cannot be directly completed based on the neural network because the training set is difficult to obtain is solved.

Description

technical field [0001] The present invention relates to the technical field of deep learning, in particular to a video processing method, a video restoration method, a device and electronic equipment. Background technique [0002] Old Vedio Reparing is mainly to restore the early unclear TV series or movies. Under normal circumstances, compared with existing films, most of the old films have problems such as low definition due to the influence of the acquisition equipment at that time, so they need to be repaired to make them clearer, so as to bring people a better visual sensory effect . [0003] At present, the restoration of old films mainly adopts manual restoration, which is time-consuming and laborious. The inventor found that although some people proposed to use deep learning to repair old films, it is difficult to obtain the training set of the neural network that can repair the old films as a whole, so it is cumbersome and complicated to use a variety of neural ne...

AI Technical Summary

Problems solved by technology

[0004] In view of this, the purpose of the present invention is to provide a video processing method, video repair method, device and electronic equipment, which can obtain a video training set for training a video repair model, and then solve the problem that cannot be directly based on the training set because it is difficult to obtain the training set. Problems with video inpainting models completing video inpainting jobs

Images