Papers › DynaVSR: Dynamic Adaptive Blind Video Super-Resolution

DynaVSR: Dynamic Adaptive Blind Video Super-Resolution

9 Nov 2020arXiv:2011.04482archive 2025-07-28

Suyoung Lee, Myungsub Choi, Kyoung Mu Lee

Most conventional supervised super-resolution (SR) algorithms assume that low-resolution (LR) data is obtained by downscaling high-resolution (HR) data with a fixed known kernel, but such an assumption often does not hold in real scenarios. Some recent blind SR algorithms have been proposed to estimate different downscaling kernels for each input LR image. However, they suffer from heavy computational overhead, making them infeasible for direct application to videos. In this work, we present DynaVSR, a novel meta-learning-based framework for real-world video SR that enables efficient downscaling model estimation and adaptation to the current input. Specifically, we train a multi-frame downscaling module with various types of synthetic blur kernels, which is seamlessly combined with a video SR network for input-aware adaptation. Experimental results show that DynaVSR consistently improves the performance of the state-of-the-art video SR models by a large margin, with an order of magnitude faster inference time compared to the existing blind SR approaches.

PaperPDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

Code

esw0116/DynaVSR officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

Meta-LearningSuper-ResolutionVideo Super-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration DynaVSR-R 1 - LPIPS 0.884 #7 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration DynaVSR-R ERQAv1.0 0.709 #7 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration DynaVSR-R FPS 0.177 #7 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration DynaVSR-R PSNR 28.377 #7 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration DynaVSR-R QRCRv1.0 0.557 #7 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration DynaVSR-R SSIM 0.865 #7 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration DynaVSR-R Subjective score 6.136 #7 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration DynaVSR-V 1 - LPIPS 0.859 #24 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration DynaVSR-V ERQAv1.0 0.643 #24 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration DynaVSR-V FPS 0.15 #24 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration DynaVSR-V PSNR 29.011 #24 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration DynaVSR-V QRCRv1.0 0.549 #24 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration DynaVSR-V SSIM 0.864 #24 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration DynaVSR-V Subjective score 4.359 #24 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Upscalers: Quality Enhancement DynaVSR PSNR 26.12 #34 of 48 Archive leaderboard report
Video Super-Resolution MSU Video Upscalers: Quality Enhancement DynaVSR SSIM 0.916 #34 of 48 Archive leaderboard report
Video Super-Resolution MSU Video Upscalers: Quality Enhancement DynaVSR VMAF 56.86 #34 of 48 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