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

Syntology This paper's arXiv id is not in Syntology's Atlas id list (549,449 ids, as this build read them; the read time is in the build record), so this page links to no Syntology page for it. The list is not the whole graph; Syntology's feed shows papers as they enter the graph.

Code

SHI-Labs/Cross-Scale-Non-Local-Attention officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
Lornatang/CSNLN-PyTorch mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Image Super-Resolution Using Very Deep Residual Channel Attention Networks (arXiv:1807.02758; that paper's own run record: 17 ran (of which 6 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
nSamsow/CSNLN-new mentioned on GitHubpytorchSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

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