BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond
This work provides strong baselines for researchers developing future video super-resolution approaches by simplifying existing complex designs.
The authors propose BasicVSR, a simplified video super-resolution (VSR) pipeline built from essential components for propagation, alignment, aggregation, and upsampling. This model achieves appealing improvements in speed and restoration quality compared to state-of-the-art algorithms.
Video super-resolution (VSR) approaches tend to have more components than the image counterparts as they need to exploit the additional temporal dimension. Complex designs are not uncommon. In this study, we wish to untangle the knots and reconsider some most essential components for VSR guided by four basic functionalities, i.e., Propagation, Alignment, Aggregation, and Upsampling. By reusing some existing components added with minimal redesigns, we show a succinct pipeline, BasicVSR, that achieves appealing improvements in terms of speed and restoration quality in comparison to many state-of-the-art algorithms. We conduct systematic analysis to explain how such gain can be obtained and discuss the pitfalls. We further show the extensibility of BasicVSR by presenting an information-refill mechanism and a coupled propagation scheme to facilitate information aggregation. The BasicVSR and its extension, IconVSR, can serve as strong baselines for future VSR approaches.