Papers › Boosting Flow-based Generative Super-Resolution Models via Learned Prior

Boosting Flow-based Generative Super-Resolution Models via Learned Prior

16 Mar 2024CVPR 2024 1arXiv:2403.10988archive 2025-07-28

Li-Yuan Tsao, Yi-Chen Lo, Chia-Che Chang, Hao-Wei Chen, Roy Tseng, Chien Feng, Chun-Yi Lee

Flow-based super-resolution (SR) models have demonstrated astonishing capabilities in generating high-quality images. However, these methods encounter several challenges during image generation, such as grid artifacts, exploding inverses, and suboptimal results due to a fixed sampling temperature. To overcome these issues, this work introduces a conditional learned prior to the inference phase of a flow-based SR model. This prior is a latent code predicted by our proposed latent module conditioned on the low-resolution image, which is then transformed by the flow model into an SR image. Our framework is designed to seamlessly integrate with any contemporary flow-based SR model without modifying its architecture or pre-trained weights. We evaluate the effectiveness of our proposed framework through extensive experiments and ablation analyses. The proposed framework successfully addresses all the inherent issues in flow-based SR models and enhances their performance in various SR scenarios. Our code is available at: https://github.com/liyuantsao/BFSR

PaperPDFConference PDFCode

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

Code

liyuantsao/BFSR 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

Image GenerationImage Super-ResolutionSuper-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Super-Resolution DIV2K val - 4x upscaling LINF-LP LPIPS 0.105 #5 of 21 Archive leaderboard report
Image Super-Resolution DIV2K val - 4x upscaling LINF-LP LRPSNR 47.3 #5 of 21 Archive leaderboard report
Image Super-Resolution DIV2K val - 4x upscaling LINF-LP PSNR 28.00 #5 of 21 Archive leaderboard report
Image Super-Resolution DIV2K val - 4x upscaling LINF-LP SSIM 0.78 #5 of 21 Archive leaderboard report
Image Super-Resolution DIV2K val - 4x upscaling SRFlow-LP LPIPS 0.109 #6 of 21 Archive leaderboard report
Image Super-Resolution DIV2K val - 4x upscaling SRFlow-LP LRPSNR 51.51 #6 of 21 Archive leaderboard report
Image Super-Resolution DIV2K val - 4x upscaling SRFlow-LP PSNR 27.51 #6 of 21 Archive leaderboard report
Image Super-Resolution DIV2K val - 4x upscaling SRFlow-LP SSIM 0.78 #6 of 21 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