Papers › Learning Task-Oriented Flows to Mutually Guide Feature Alignment in Synthesized and...

Learning Task-Oriented Flows to Mutually Guide Feature Alignment in Synthesized and Real Video Denoising

25 Aug 2022arXiv:2208.11803archive 2025-07-28

JieZhang Cao, Qin Wang, Jingyun Liang, Yulun Zhang, Kai Zhang, Radu Timofte, Luc van Gool

Video denoising aims at removing noise from videos to recover clean ones. Some existing works show that optical flow can help the denoising by exploiting the additional spatial-temporal clues from nearby frames. However, the flow estimation itself is also sensitive to noise, and can be unusable under large noise levels. To this end, we propose a new multi-scale refined optical flow-guided video denoising method, which is more robust to different noise levels. Our method mainly consists of a denoising-oriented flow refinement (DFR) module and a flow-guided mutual denoising propagation (FMDP) module. Unlike previous works that directly use off-the-shelf flow solutions, DFR first learns robust multi-scale optical flows, and FMDP makes use of the flow guidance by progressively introducing and refining more flow information from low resolution to high resolution. Together with real noise degradation synthesis, the proposed multi-scale flow-guided denoising network achieves state-of-the-art performance on both synthetic Gaussian denoising and real video denoising. The codes will be made publicly available.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DenoisingOptical Flow EstimationVideo Denoising

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Denoising DAVIS sigma10 ReViD PSNR 41.03 #1 of 6 Archive leaderboard report
Video Denoising DAVIS sigma20 ReViD PSNR 38.5 #1 of 7 Archive leaderboard report
Video Denoising DAVIS sigma30 ReViD PSNR 36.97 #1 of 7 Archive leaderboard report
Video Denoising DAVIS sigma40 ReViD PSNR 35.83 #1 of 8 Archive leaderboard report
Video Denoising DAVIS sigma50 ReViD PSNR 34.9 #1 of 8 Archive leaderboard report
Video Denoising Set8 sigma10 ReViD PSNR 38.07 #1 of 6 Archive leaderboard report
Video Denoising Set8 sigma20 ReViD PSNR 35.35 #1 of 7 Archive leaderboard report
Video Denoising Set8 sigma30 ReViD PSNR 33.78 #1 of 7 Archive leaderboard report
Video Denoising Set8 sigma40 ReViD PSNR 32.66 #1 of 8 Archive leaderboard report
Video Denoising Set8 sigma50 ReViD PSNR 31.77 #1 of 9 Archive leaderboard report
Video Denoising VideoLQ ReViD BRISQUE 29.0212 #1 of 2 Archive leaderboard report
Video Denoising VideoLQ ReViD NIQE 4.0205 #1 of 2 Archive leaderboard report
Video Denoising VideoLQ ReViD PIQE 45.0768 #1 of 2 Archive leaderboard report
Video Denoising VideoLQ RealBasicVSR BRISQUE 29.2103 #2 of 2 Archive leaderboard report
Video Denoising VideoLQ RealBasicVSR NIQE 4.2167 #2 of 2 Archive leaderboard report
Video Denoising VideoLQ RealBasicVSR PIQE 48.0369 #2 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections