Official repository of BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment.

Update 8/4/2021. BasicVSR is finally out! The model can be found here (temporally, PR in progress). The pretrained weights and IconVSR is coming!

BasicVSR is a simple yet efficient baseline for video super-resolution. It consists of only generic components such as residual blocks and optical flow.

In this study, we redesign BasicVSR by proposing second-order grid propagation and flow-guided deformable alignment.

Dependencies and Installation · The code is based on the old version of BasicSR, Please install the BasicSR framework first. · Pytorch=1.51. Training.

This is the official repository of Investigating Tradeoffs in Real-World Video Super-Resolution, arXiv. This repository contains codes, colab, video demos of ...

BasicVSR is a public AI algorithm. We have enhanced the public model to achieve better visual quality and less computational complexity.

The state-of-the-art method BasicVSR adopts bidirectional propagation with feature alignment to effectively exploit information from the entire input video.

Oct 26, 2022 · To reduce the resolution by 2 times instead of 4, you can just simply reduce the number of strided conv and pixel shuffle from 2 to 1.

Improving Video Super-Resolution with Enhanced Propagation and Alignment, based on https://github.com/ckkelvinchan/BasicVSR_PlusPlus.