Resolution improvement based film and TV works renovation method

Abstract

The present invention provides a resolution improvement based film and TV works renovation method for film and TV works with low resolution and low definition. The method includes the specific steps of firstly, acquiring a resolution of an original video and a target resolution, and calculating a zoom ratio; then, segmenting an input video into an image frame set according to a certain segmentation manner; then, performing conversion according to a prestored mapping relation, so as to obtain high resolution video frames; and finally, combing the high resolution video frames to obtain a high resolution video. The prestored mapping relation is obtained by learning a hybrid expert model, and the process is finished offline in a computer. The method has the advantages of good adaptability, fast speed, good effect, expandability and so on.

Description

technical field [0001] The invention belongs to the field of computer vision and image processing, and relates to a method for renovating film and television works, in particular to a method and system for renovating film and television works based on resolution enhancement. Background technique [0002] With the development of video acquisition, transmission, storage, and display technologies, film and television works are constantly developing towards high resolution. People enjoy more and more tastes in video, and they are constantly pursuing high-resolution and high-definition film and television works. At the same time, the emergence of high-resolution display devices (such as 4K and 5K TVs and monitors) has made it possible to popularize high-resolution film and television works. [0003] However, on the other hand, many classic film and television works with a long history still have low resolution, low definition, and poor visual effects due to technical limitations...

AI Technical Summary

Problems solved by technology

The interpolation algorithm is simple and fast, but it is prone to "mosaic" effect or over-smoothing phenomenon; the reconstruction-based algorithm uses the similarity of multi-frame images for registration and reconstruction, but such algorithms often simply combine multi-frame images, and the effect is not ideal; The learning-based algorithm mainly uses a certain amount of training data to obtain the mapping relationship between low-resolution video and high-resolution video according to specific algorithm training. This type of algorithm has relatively high requirements for the model and is prone to over-fitting or under-fitting. And the amount of calculation is large, the speed is slow, and the practicability is not high

It can be said that the above-mentioned video resolution improvement problem has been plagued by the majority of users.

Images