# Learning for Video Super-Resolution through HR Optical Flow Estimation

Source: [Learning for Video Super-Resolution through HR Optical Flow Estimation](<https://www.sota2.com/research/paper/68fa64f71e209131cea076b9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:02:14.777Z

Authors: Longguang Wang, Yulan Guo, Zaiping Lin, Xinpu Deng, Wei An

Published: 2018-09-23T10:30:28.000Z

## Abstract

Video super-resolution (SR) aims to generate a sequence of high-resolution (HR) frames with plausible and temporally consistent details from their low-resolution (LR) counterparts. The generation of accurate correspondence plays a significant role in video SR. It is demonstrated by traditional video SR methods that simultaneous SR of both images and optical flows can provide accurate correspondences and better SR results. However, LR optical flows are used in existing deep learning based methods for correspondence generation. In this paper, we propose an end-to-end trainable video SR framework to super-resolve both images and optical flows. Specifically, we first propose an optical flow reconstruction network (OFRnet) to infer HR optical flows in a coarse-to-fine manner. Then, motion compensation is performed according to the HR optical flows. Finally, compensated LR inputs are fed to a super-resolution network (SRnet) to generate the SR results. Extensive experiments demonstrate that HR optical flows provide more accurate correspondences than their LR counterparts and improve both accuracy and consistency performance. Comparative results on the Vid4 and DAVIS-10 datasets show that our framework achieves the state-of-the-art performance.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Video Super-Resolution on Vid4 x4 upscaling (test)](<https://www.sota2.com/research/sota/video-super-resolution-on-vid4-x4-upscaling-test.md>): Video Super-Resolution; Vid4 x4 upscaling (test); PSNR: 26.19.

- [Video Super-Resolution on DAVIS-10](<https://www.sota2.com/research/sota/video-super-resolution-on-davis-10.md>): Video Super-Resolution; DAVIS-10; PSNR: 34.32.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1809.08573>)

[PDF](<https://arxiv.org/pdf/1809.08573.pdf>)

[Implementation](<https://github.com/LongguangWang/SOF-VSR-Super-Resolving-Optical-Flow-for-Video-Super-Resolution->)