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. Codes and models will be released to MMEditing.
翻译：常规结构是一种流行的超分辨率视频任务框架选择。 BasicVSR采用最先进的方法,双向传播和功能匹配,以有效地利用整个输入视频的信息。在本研究中,我们重新设计基本VSR,提出二阶网格传播和流程导导变形调整。我们显示,通过强化传播和校正,通过增强传播和校正来增强经常框架的权能,可以更有效地利用错配视频框架的时空信息。在类似的计算限制下,新组件导致性能的改善。特别是,我们的模型BasicVSR++在PSNR中比基本VSR多0.82 dB, 比基本VSR多出0.82 dB,参数相似。除了视频超分辨率外,基本VSR+++还概括了其他视频恢复任务,如压缩视频增强等。在2021 NTIRE中,基本VSR++在视频超分辨率和压缩视频增强挑战中获得了3名冠军和1次赛跑跑。代码和模型将发布MMEditinginging。
相关内容
微信扫码咨询专知VIP会员