Papers › Single Image Super-Resolution via a Holistic Attention Network

Single Image Super-Resolution via a Holistic Attention Network

20 Aug 2020ECCV 2020 8arXiv:2008.08767archive 2025-07-28

Ben Niu, Weilei Wen, Wenqi Ren, Xiangde Zhang, Lianping Yang, Shuzhen Wang, Kaihao Zhang, Xiaochun Cao, Haifeng Shen

Informative features play a crucial role in the single image super-resolution task. Channel attention has been demonstrated to be effective for preserving information-rich features in each layer. However, channel attention treats each convolution layer as a separate process that misses the correlation among different layers. To address this problem, we propose a new holistic attention network (HAN), which consists of a layer attention module (LAM) and a channel-spatial attention module (CSAM), to model the holistic interdependencies among layers, channels, and positions. Specifically, the proposed LAM adaptively emphasizes hierarchical features by considering correlations among layers. Meanwhile, CSAM learns the confidence at all the positions of each channel to selectively capture more informative features. Extensive experiments demonstrate that the proposed HAN performs favorably against the state-of-the-art single image super-resolution approaches.

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

04RR/SOTA-Vision mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (arXiv:2010.11929; that paper's own run record: 307 ran (of which 165 constructed an object rather than computing a result; 286 with no instrument failure: 8 honoured, 2 violated, 276 with no contract checked; 21 where Syntology's instrument failed) · 112 unverified) and MLP-Mixer: An all-MLP Architecture for Vision (arXiv:2105.01601; that paper's own run record: 114 ran (of which 77 constructed an object rather than computing a result; 104 with no instrument failure: 2 honoured, 1 violated, 101 with no contract checked; 10 where Syntology's instrument failed) · 20 unverified); nothing checks that they implement this paper's method. report
wwlCape/HAN 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

Image Super-ResolutionSuper-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Super-Resolution BSD100 - 2x upscaling HAN+ PSNR 32.45 #15 of 30 Archive leaderboard report
Image Super-Resolution BSD100 - 2x upscaling HAN+ SSIM 0.8431 #15 of 30 Archive leaderboard report
Image Super-Resolution BSD100 - 3x upscaling HAN+ PSNR 29.41 #9 of 21 Archive leaderboard report
Image Super-Resolution BSD100 - 3x upscaling HAN+ SSIM 0.8116 #9 of 21 Archive leaderboard report
Image Super-Resolution BSD100 - 4x upscaling HAN+ PSNR 27.85 #16 of 71 Archive leaderboard report
Image Super-Resolution BSD100 - 4x upscaling HAN+ SSIM 0.7454 #16 of 71 Archive leaderboard report
Image Super-Resolution BSD100 - 8x upscaling HAN+ PSNR 25.04 #2 of 6 Archive leaderboard report
Image Super-Resolution BSD100 - 8x upscaling HAN+ SSIM 0.6075 #2 of 6 Archive leaderboard report
Image Super-Resolution Manga109 - 2x upscaling HAN+ PSNR 39.62 #12 of 21 Archive leaderboard report
Image Super-Resolution Manga109 - 2x upscaling HAN+ SSIM 0.9787 #12 of 21 Archive leaderboard report
Image Super-Resolution Manga109 - 3x upscaling HAN+ PSNR 34.87 #10 of 17 Archive leaderboard report
Image Super-Resolution Manga109 - 3x upscaling HAN+ SSIM 0.9509 #10 of 17 Archive leaderboard report
Image Super-Resolution Manga109 - 4x upscaling HAN+ PSNR 31.73 #24 of 50 Archive leaderboard report
Image Super-Resolution Manga109 - 4x upscaling HAN+ SSIM 0.9207 #24 of 50 Archive leaderboard report
Image Super-Resolution Manga109 - 8x upscaling HAN+ PSNR 25.54 #3 of 5 Archive leaderboard report
Image Super-Resolution Manga109 - 8x upscaling HAN+ SSIM 0.8080 #3 of 5 Archive leaderboard report
Image Super-Resolution Set14 - 2x upscaling HAN+ PSNR 34.24 #15 of 35 Archive leaderboard report
Image Super-Resolution Set14 - 2x upscaling HAN+ SSIM 0.9224 #15 of 35 Archive leaderboard report
Image Super-Resolution Set14 - 3x upscaling HAN+ PSNR 30.79 #12 of 24 Archive leaderboard report
Image Super-Resolution Set14 - 3x upscaling HAN+ SSIM 0.8487 #12 of 24 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling HAN+ PSNR 28.99 #31 of 104 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling HAN+ SSIM 0.7907 #31 of 104 Archive leaderboard report
Image Super-Resolution Set14 - 8x upscaling HAN+ PSNR 25.39 #3 of 7 Archive leaderboard report
Image Super-Resolution Set14 - 8x upscaling HAN+ SSIM 0.6552 #3 of 7 Archive leaderboard report
Image Super-Resolution Set5 - 2x upscaling HAN+ PSNR 38.33 #15 of 41 Archive leaderboard report
Image Super-Resolution Set5 - 2x upscaling HAN+ SSIM 0.9299 #15 of 41 Archive leaderboard report
Image Super-Resolution Set5 - 3x upscaling HAN+ PSNR 34.85 #14 of 32 Archive leaderboard report
Image Super-Resolution Set5 - 3x upscaling HAN+ SSIM 0.9300 #14 of 32 Archive leaderboard report
Image Super-Resolution Set5 - 8x upscaling HAN+ PSNR 27.47 #3 of 8 Archive leaderboard report
Image Super-Resolution Set5 - 8x upscaling HAN+ SSIM 0.7920 #3 of 8 Archive leaderboard report
Image Super-Resolution Urban100 - 2x upscaling HAN+ PSNR 33.53 #12 of 29 Archive leaderboard report
Image Super-Resolution Urban100 - 2x upscaling HAN+ SSIM 0.9398 #12 of 29 Archive leaderboard report
Image Super-Resolution Urban100 - 3x upscaling HAN+ PSNR 29.21 #12 of 22 Archive leaderboard report
Image Super-Resolution Urban100 - 3x upscaling HAN+ SSIM 0.8710 #12 of 22 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling HAN+ PSNR 27.02 #24 of 65 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling HAN+ SSIM 0.8131 #24 of 65 Archive leaderboard report
Image Super-Resolution Urban100 - 8x upscaling HAN+ PSNR 23.20 #3 of 5 Archive leaderboard report
Image Super-Resolution Urban100 - 8x upscaling HAN+ SSIM 0.6518 #3 of 5 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

Convolution

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