Video super-resolution method based on time attention and cyclic feedback network

Abstract

The invention provides a video super-resolution method based on time attention and a cyclic feedback network. The characteristic that the contribution degrees of visual information provided by adjacent frames with different distances from a target frame to a super-resolution reconstruction effect are different, a feedback mechanism of a human visual system and a cyclic feedback guidance characteristic in a human new knowledge learning process are applied to a video super-resolution technology; a time attention module is adopted to learn an attention map of a video sequence on a time axis, so that the contribution of adjacent frames with different time degrees to a final reconstruction effect can be effectively distinguished; a video sequence is rearranged and then is subjected to cyclic feedback super-division by a cyclic feedback module, and finally a super-resolution network model is obtained, and the model has the characteristic of emphatically learning information with high contribution to super-division reconstruction and strong high-level feature learning ability, so that the video super-resolution effect is improved.

Description

technical field [0001] The invention relates to the technical field of video processing, in particular to a video super-resolution method based on temporal attention and loop feedback network. Background technique [0002] Video super-resolution methods, which generate high-resolution videos from low-resolution videos, have been extensively studied for decades as a typical computer vision problem. Not only is it important in theory, but it is also urgently needed in practical applications. For example, in terms of video surveillance, banks, stations, airports, residential areas, etc. will have multiple surveillance cameras. Through video super-resolution technology, the video quality can be improved, and it is convenient to observe the detailed information of people and objects; in terms of traffic management, due to The scene observed by the camera is large, and it is impossible to obtain the detailed information of high-speed vehicles and passing pedestrians. Using the mu...

AI Technical Summary

Problems solved by technology

In the existing methods, (1) in terms of timing information utilization, the characteristics of different contributions of visual information provided by adjacent frames with different distances from the target frame to the super-resolution reconstruction effect have not been fully utilized; (2) human vision has not been fully utilized Feedback mechanisms common in systems, and the cyclical feedback-guided nature of human learning of new knowledge

Images