BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond

TL;DR

BasicVSR simplifies video super-resolution by focusing on four essential components, achieving improved speed and quality, and providing a strong, extensible baseline for future research.

Contribution

The paper introduces BasicVSR, a streamlined VSR pipeline based on four core functionalities, with extensions demonstrating enhanced information aggregation.

Findings

Achieves better speed and restoration quality than many state-of-the-art methods.

Systematic analysis explains the source of performance gains.

Extensions like IconVSR further improve information aggregation.

Abstract

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.