Papers › RFSR: Improving ISR Diffusion Models via Reward Feedback Learning

RFSR: Improving ISR Diffusion Models via Reward Feedback Learning

4 Dec 2024arXiv:2412.03268archive 2025-07-28

Xiaopeng Sun, Qinwei Lin, Yu Gao, Yujie Zhong, Chengjian Feng, Dengjie Li, Zheng Zhao, Jie Hu, Lin Ma

Generative diffusion models (DM) have been extensively utilized in image super-resolution (ISR). Most of the existing methods adopt the denoising loss from DDPMs for model optimization. We posit that introducing reward feedback learning to finetune the existing models can further improve the quality of the generated images. In this paper, we propose a timestep-aware training strategy with reward feedback learning. Specifically, in the initial denoising stages of ISR diffusion, we apply low-frequency constraints to super-resolution (SR) images to maintain structural stability. In the later denoising stages, we use reward feedback learning to improve the perceptual and aesthetic quality of the SR images. In addition, we incorporate Gram-KL regularization to alleviate stylization caused by reward hacking. Our method can be integrated into any diffusion-based ISR model in a plug-and-play manner. Experiments show that ISR diffusion models, when fine-tuned with our method, significantly improve the perceptual and aesthetic quality of SR images, achieving excellent subjective results. Code: https://github.com/sxpro/RFSR

PaperPDFCode

Code

sxpro/rfsr officialmentioned in paperpytorch 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

Blind Super-ResolutionImage Super-ResolutionModel OptimizationSuper-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Blind Super-Resolution DRealSR SeeSR+RFSR clipiqa 0.7596 #1 of 1 Archive leaderboard report
Blind Super-Resolution DRealSR SeeSR+RFSR maniqa 0.5922 #1 of 1 Archive leaderboard report
Blind Super-Resolution DRealSR SeeSR+RFSR musiq 67.48 #1 of 1 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.

Methods

ADOPTDiffusion

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