Papers › Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive...

Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining

2 Jun 2020CVPR 2020 6arXiv:2006.01424archive 2025-07-28

Yiqun Mei, Yuchen Fan, Yuqian Zhou, Lichao Huang, Thomas S. Huang, Humphrey Shi

Deep convolution-based single image super-resolution (SISR) networks embrace the benefits of learning from large-scale external image resources for local recovery, yet most existing works have ignored the long-range feature-wise similarities in natural images. Some recent works have successfully leveraged this intrinsic feature correlation by exploring non-local attention modules. However, none of the current deep models have studied another inherent property of images: cross-scale feature correlation. In this paper, we propose the first Cross-Scale Non-Local (CS-NL) attention module with integration into a recurrent neural network. By combining the new CS-NL prior with local and in-scale non-local priors in a powerful recurrent fusion cell, we can find more cross-scale feature correlations within a single low-resolution (LR) image. The performance of SISR is significantly improved by exhaustively integrating all possible priors. Extensive experiments demonstrate the effectiveness of the proposed CS-NL module by setting new state-of-the-arts on multiple SISR benchmarks.

PaperPDFConference PDFCode

Code

SHI-Labs/Cross-Scale-Non-Local-Attention officialmentioned in papermentioned on GitHubpytorch report
Lornatang/CSNLN-PyTorch mentioned on GitHubpytorchApache-2.0 report
nSamsow/CSNLN-new 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

Feature CorrelationImage Super-ResolutionSuper-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Super-Resolution BSD100 - 2x upscaling CSNLN PSNR 32.4 #17 of 30 Archive leaderboard report
Image Super-Resolution BSD100 - 2x upscaling CSNLN SSIM 0.9024 #17 of 30 Archive leaderboard report
Image Super-Resolution BSD100 - 3x upscaling CSNLN PSNR 29.33 #12 of 21 Archive leaderboard report
Image Super-Resolution BSD100 - 3x upscaling CSNLN SSIM 0.8105 #12 of 21 Archive leaderboard report
Image Super-Resolution BSD100 - 4x upscaling CSNLN PSNR 27.8 #19 of 71 Archive leaderboard report
Image Super-Resolution BSD100 - 4x upscaling CSNLN SSIM 0.7439 #19 of 71 Archive leaderboard report
Image Super-Resolution Manga109 - 2x upscaling CSNLN PSNR 39.37 #13 of 21 Archive leaderboard report
Image Super-Resolution Manga109 - 2x upscaling CSNLN SSIM 0.9785 #13 of 21 Archive leaderboard report
Image Super-Resolution Manga109 - 3x upscaling CSNLN PSNR 34.45 #11 of 17 Archive leaderboard report
Image Super-Resolution Manga109 - 3x upscaling CSNLN SSIM 0.9502 #11 of 17 Archive leaderboard report
Image Super-Resolution Manga109 - 4x upscaling CSNLN PSNR 31.43 #25 of 50 Archive leaderboard report
Image Super-Resolution Manga109 - 4x upscaling CSNLN SSIM 0.9201 #25 of 50 Archive leaderboard report
Image Super-Resolution Set14 - 2x upscaling CSNLN PSNR 34.12 #16 of 35 Archive leaderboard report
Image Super-Resolution Set14 - 2x upscaling CSNLN SSIM 0.9223 #16 of 35 Archive leaderboard report
Image Super-Resolution Set14 - 3x upscaling CSNLN PSNR 30.66 #13 of 24 Archive leaderboard report
Image Super-Resolution Set14 - 3x upscaling CSNLN SSIM 0.8482 #13 of 24 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling CSNLN PSNR 28.95 #34 of 104 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling CSNLN SSIM 0.7888 #34 of 104 Archive leaderboard report
Image Super-Resolution Set5 - 2x upscaling CSNLN PSNR 38.28 #17 of 41 Archive leaderboard report
Image Super-Resolution Set5 - 2x upscaling CSNLN SSIM 0.9616 #17 of 41 Archive leaderboard report
Image Super-Resolution Set5 - 3x upscaling CSNLN PSNR 34.74 #15 of 32 Archive leaderboard report
Image Super-Resolution Set5 - 3x upscaling CSNLN SSIM 0.9300 #15 of 32 Archive leaderboard report
Image Super-Resolution Urban100 - 2x upscaling CSNLN PSNR 33.25 #14 of 29 Archive leaderboard report
Image Super-Resolution Urban100 - 2x upscaling CSNLN SSIM 0.9386 #14 of 29 Archive leaderboard report
Image Super-Resolution Urban100 - 3x upscaling CSNLN PSNR 29.13 #13 of 22 Archive leaderboard report
Image Super-Resolution Urban100 - 3x upscaling CSNLN SSIM 0.8712 #13 of 22 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling CSNLN PSNR 27.22 #19 of 65 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling CSNLN SSIM 0.8168 #19 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.

Methods

Cross-Scale Non-Local Attention

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