BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment

• Published in: Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 5962 - 5971
• Main Authors: Chan, Kelvin C.K., Zhou, Shangchen, Xu, Xiangyu, Loy, Chen Change
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2022
• Subjects: Computational modeling; Computer vision; Low-level vision; Pattern recognition; Spatiotemporal phenomena; Superresolution; Task analysis
• ISSN: 1063-6919
• DOI: 10.1109/CVPR52688.2022.00588

A recurrent structure is a popular framework choice for the task of video super-resolution. The state-of-the-art method BasicVSR adopts bidirectional propagation with feature alignment to effectively exploit information from the entire input video. In this study, we redesign BasicVsr by proposing se...