Papers › NAFSSR: Stereo Image Super-Resolution Using NAFNet

NAFSSR: Stereo Image Super-Resolution Using NAFNet

19 Apr 2022arXiv:2204.08714archive 2025-07-28

Xiaojie Chu, Liangyu Chen, Wenqing Yu

Stereo image super-resolution aims at enhancing the quality of super-resolution results by utilizing the complementary information provided by binocular systems. To obtain reasonable performance, most methods focus on finely designing modules, loss functions, and etc. to exploit information from another viewpoint. This has the side effect of increasing system complexity, making it difficult for researchers to evaluate new ideas and compare methods. This paper inherits a strong and simple image restoration model, NAFNet, for single-view feature extraction and extends it by adding cross attention modules to fuse features between views to adapt to binocular scenarios. The proposed baseline for stereo image super-resolution is noted as NAFSSR. Furthermore, training/testing strategies are proposed to fully exploit the performance of NAFSSR. Extensive experiments demonstrate the effectiveness of our method. In particular, NAFSSR outperforms the state-of-the-art methods on the KITTI 2012, KITTI 2015, Middlebury, and Flickr1024 datasets. With NAFSSR, we won 1st place in the NTIRE 2022 Stereo Image Super-resolution Challenge. Codes and models will be released at https://github.com/megvii-research/NAFNet.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

megvii-research/NAFNet officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Simple Baselines for Image Restoration (arXiv:2204.04676; that paper's own run record: 23 ran (of which 8 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 0 violated, 12 with no contract checked; 9 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
megvii-research/TLC mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
megvii-research/tlsc mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
setsunil/dsdnet mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
dslisleedh/NAFNet-flax jaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Simple Baselines for Image Restoration (arXiv:2204.04676; that paper's own run record: 23 ran (of which 8 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 0 violated, 12 with no contract checked; 9 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. 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 RestorationImage Super-ResolutionStereo Image Super-ResolutionSuper-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Stereo Image Super-Resolution Flickr1024 - 2x upscaling NAFSSR-L PSNR 29.68 #3 of 10 Archive leaderboard report
Stereo Image Super-Resolution Flickr1024 - 2x upscaling NAFSSR-B PSNR 29.54 #4 of 10 Archive leaderboard report
Stereo Image Super-Resolution Flickr1024 - 4x upscaling NAFSSR-L PSNR 24.17 #2 of 8 Archive leaderboard report
Stereo Image Super-Resolution Flickr1024 - 4x upscaling NAFSSR-B PSNR 24.07 #3 of 8 Archive leaderboard report
Stereo Image Super-Resolution KITTI2012 - 2x upscaling NAFSSR-L PSNR 31.60 #3 of 5 Archive leaderboard report
Stereo Image Super-Resolution KITTI2012 - 2x upscaling NAFSSR-B PSNR 31.55 #4 of 5 Archive leaderboard report
Stereo Image Super-Resolution KITTI2012 - 4x upscaling NAFSSR-L PSNR 27.12 #2 of 9 Archive leaderboard report
Stereo Image Super-Resolution KITTI2012 - 4x upscaling NAFSSR-B PSNR 27.08 #3 of 9 Archive leaderboard report
Stereo Image Super-Resolution KITTI2015 - 2x upscaling NAFSSR-L PSNR 31.25 #2 of 9 Archive leaderboard report
Stereo Image Super-Resolution KITTI2015 - 2x upscaling NAFSSR-B PSNR 31.22 #3 of 9 Archive leaderboard report
Stereo Image Super-Resolution KITTI2015 - 4x upscaling NAFSSR-L PSNR 26.96 #1 of 9 Archive leaderboard report
Stereo Image Super-Resolution KITTI2015 - 4x upscaling NAFSSR-B PSNR 26.91 #2 of 9 Archive leaderboard report
Stereo Image Super-Resolution Middlebury - 2x upscaling NAFSSR-L PSNR 35.88 #2 of 9 Archive leaderboard report
Stereo Image Super-Resolution Middlebury - 2x upscaling NAFSSR-B PSNR 35.68 #4 of 9 Archive leaderboard report
Stereo Image Super-Resolution Middlebury - 4x upscaling NAFSSR-L PSNR 30.20 #2 of 9 Archive leaderboard report
Stereo Image Super-Resolution Middlebury - 4x upscaling NAFSSR-B PSNR 30.04 #3 of 9 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

NAFNet

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