BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment
TL
TL;DR
This study redesigns BasicVsr by proposing second-order grid propagation and flow-guided deformable alignment, and shows that by empowering the re-current framework with enhanced propagation and align-ment, one can exploit spatiotemporal information across misaligned video frames more effectively.
Abstract
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 second-order grid propagation and flow-guided deformable alignment. We show that by empowering the re-current framework with enhanced propagation and align-ment, one can exploit spatiotemporal information across misaligned video frames more effectively. The new components lead to an improved performance under a simi-lar computational constraint. In particular, our model Ba-sicVSR++ surpasses BasicVSR by a significant 0.82 dB in PSNR with similar number of parameters. BasicVSR++ is generalizable to other video restoration tasks, and obtains three champions and one first runner-up in NTIRE 2021 video restoration challenge.
References47 items
1
Investigating Tradeoffs in Real-World Video Super-Resolution
2
Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
3
Video Super-Resolution Transformer
4
NTIRE 2021 Challenge on Video Super-Resolution
5