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

S-Lab, Nanyang Technological University

Improvements over BasicVSR. BasicVSR++ consists of two effective modifications for improving propagation and alignment. The proposed second-order grid propagation and flow-guided deformable alignment allow BasicVSR++ to significantly outperform existing state of the arts with comparable runtime.

Highlights

  1. BasicVSR++ won 3 champions and 1 runner-up in NTIRE 2021 Video Restoration and Enhancement Challenge.
  2. BasicVSR++ surpasses existing state-of-the-art VSR methods by a large margin with comparable complexity.

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 recurrent framework with the enhanced propagation and alignment, one can exploit spatiotemporal information across misaligned video frames more effectively. The new components lead to an improved performance under a similar computational constraint. In particular, our model BasicVSR++ surpasses BasicVSR by 0.82 dB in PSNR with similar number of parameters. In addition to video super-resolution, BasicVSR++ generalizes well to other video restoration tasks such as compressed video enhancement. In NTIRE 2021, BasicVSR++ obtains three champions and one runner-up in the Video Super-Resolution and Compressed Video Enhancement Challenges.

Network Details

Left: The overview of BasicVSR++; Right: The proposed flow-guided deformable alignment module. See our paper for more details.

Results

Results of 4x super-resolution: By better employing the information from the video, BasicVSR++ successfully reconstructs the finer details.


Citation

@article{chan2021basicvsr++,
  author = {Chan, Kelvin C.K. and Zhou, Shangchen and Xu, Xiangyu and Loy, Chen Change},
  title = {BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment},
  booktitle = {arXiv preprint arXiv:2104.13371},
  year = {2021}
}
          

Contact

If you have any question, please contact Kelvin Chan at chan0899@e.ntu.edu.sg.