</> Code with Papers by Syntology

Papers › Structure-Preserving Super Resolution with Gradient Guidance

Structure-Preserving Super Resolution with Gradient Guidance

29 Mar 2020CVPR 2020 6arXiv:2003.13081archive 2025-07-28

Cheng Ma, Yongming Rao, Yean Cheng, Ce Chen, Jiwen Lu, Jie zhou

Structures matter in single image super resolution (SISR). Recent studies benefiting from generative adversarial network (GAN) have promoted the development of SISR by recovering photo-realistic images. However, there are always undesired structural distortions in the recovered images. In this paper, we propose a structure-preserving super resolution method to alleviate the above issue while maintaining the merits of GAN-based methods to generate perceptual-pleasant details. Specifically, we exploit gradient maps of images to guide the recovery in two aspects. On the one hand, we restore high-resolution gradient maps by a gradient branch to provide additional structure priors for the SR process. On the other hand, we propose a gradient loss which imposes a second-order restriction on the super-resolved images. Along with the previous image-space loss functions, the gradient-space objectives help generative networks concentrate more on geometric structures. Moreover, our method is model-agnostic, which can be potentially used for off-the-shelf SR networks. Experimental results show that we achieve the best PI and LPIPS performance and meanwhile comparable PSNR and SSIM compared with state-of-the-art perceptual-driven SR methods. Visual results demonstrate our superiority in restoring structures while generating natural SR images.

PaperPDFConference PDFCode

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

Code

Maclory/SPSR officialmentioned in papermentioned on GitHubpytorch report
szWingLee/spsr-master mentioned 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 Super-ResolutionSSIMSuper-Resolution

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Super-Resolution BSD100 - 4x upscaling SPSR LPIPS 0.1611 #61 of 71 Archive leaderboard report
Image Super-Resolution BSD100 - 4x upscaling SPSR PSNR 25.505 #61 of 71 Archive leaderboard report
Image Super-Resolution BSD100 - 4x upscaling SPSR SSIM 0.6576 #61 of 71 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling SPSR PSNR 26.64 #97 of 104 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling SPSR SSIM 0.7930 #97 of 104 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling SPSR LPIPS 0.1184 #58 of 65 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling SPSR PSNR 24.799 #58 of 65 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling SPSR Perceptual Index 3.5511 #58 of 65 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling SPSR SSIM 0.9481 #58 of 65 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