Papers › Image Super-Resolution via Attention based Back Projection Networks

Image Super-Resolution via Attention based Back Projection Networks

10 Oct 2019arXiv:1910.04476archive 2025-07-28

Zhi-Song Liu, Li-Wen Wang, Chu-Tak Li, Wan-Chi Siu, Yui-Lam Chan

Deep learning based image Super-Resolution (SR) has shown rapid development due to its ability of big data digestion. Generally, deeper and wider networks can extract richer feature maps and generate SR images with remarkable quality. However, the more complex network we have, the more time consumption is required for practical applications. It is important to have a simplified network for efficient image SR. In this paper, we propose an Attention based Back Projection Network (ABPN) for image super-resolution. Similar to some recent works, we believe that the back projection mechanism can be further developed for SR. Enhanced back projection blocks are suggested to iteratively update low- and high-resolution feature residues. Inspired by recent studies on attention models, we propose a Spatial Attention Block (SAB) to learn the cross-correlation across features at different layers. Based on the assumption that a good SR image should be close to the original LR image after down-sampling. We propose a Refined Back Projection Block (RBPB) for final reconstruction. Extensive experiments on some public and AIM2019 Image Super-Resolution Challenge datasets show that the proposed ABPN can provide state-of-the-art or even better performance in both quantitative and qualitative measurements.

PaperPDFCode

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

Code

Holmes-Alan/ABPN officialmentioned in papermentioned 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-ResolutionSuper-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Super-Resolution BSD100 - 16x upscaling ABPN PSNR 22.72 #1 of 1 Archive leaderboard report
Image Super-Resolution BSD100 - 16x upscaling ABPN SSIM 0.512 #1 of 1 Archive leaderboard report
Image Super-Resolution BSD100 - 4x upscaling ABPN PSNR 27.82 #18 of 71 Archive leaderboard report
Image Super-Resolution BSD100 - 4x upscaling ABPN SSIM 0.743 #18 of 71 Archive leaderboard report
Image Super-Resolution BSD100 - 8x upscaling ABPN PSNR 24.99 #3 of 6 Archive leaderboard report
Image Super-Resolution BSD100 - 8x upscaling ABPN SSIM 0.604 #3 of 6 Archive leaderboard report
Image Super-Resolution DIV2K val - 16x upscaling ABPN PSNR 24.38 #1 of 1 Archive leaderboard report
Image Super-Resolution DIV2K val - 16x upscaling ABPN SSIM 0.641 #1 of 1 Archive leaderboard report
Image Super-Resolution DIV8K val - 16x upscaling ABPN PSNR 26.71 #3 of 3 Archive leaderboard report
Image Super-Resolution DIV8K val - 16x upscaling ABPN SSIM 0.65 #3 of 3 Archive leaderboard report
Image Super-Resolution Manga109 - 16x upscaling ABPN PSNR 21.25 #1 of 1 Archive leaderboard report
Image Super-Resolution Manga109 - 16x upscaling ABPN SSIM 0.673 #1 of 1 Archive leaderboard report
Image Super-Resolution Manga109 - 4x upscaling ABPN PSNR 31.79 #22 of 50 Archive leaderboard report
Image Super-Resolution Manga109 - 4x upscaling ABPN SSIM 0.921 #22 of 50 Archive leaderboard report
Image Super-Resolution Manga109 - 8x upscaling ABPN PSNR 25.29 #4 of 5 Archive leaderboard report
Image Super-Resolution Manga109 - 8x upscaling ABPN SSIM 0.802 #4 of 5 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling ABPN PSNR 28.94 #36 of 104 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling ABPN SSIM 0.789 #36 of 104 Archive leaderboard report
Image Super-Resolution Set14 - 8x upscaling ABPN PSNR 25.08 #4 of 7 Archive leaderboard report
Image Super-Resolution Set14 - 8x upscaling ABPN SSIM 0.638 #4 of 7 Archive leaderboard report
Image Super-Resolution Set5 - 8x upscaling ABPN PSNR 27.25 #5 of 8 Archive leaderboard report
Image Super-Resolution Set5 - 8x upscaling ABPN SSIM 0.786 #5 of 8 Archive leaderboard report
Image Super-Resolution Urban100 - 16x upscaling ABPN PSNR 20.39 #1 of 1 Archive leaderboard report
Image Super-Resolution Urban100 - 16x upscaling ABPN SSIM 0.515 #1 of 1 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling ABPN PSNR 27.06 #22 of 65 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling ABPN SSIM 0.811 #22 of 65 Archive leaderboard report
Image Super-Resolution Urban100 - 8x upscaling ABPN PSNR 23.04 #5 of 5 Archive leaderboard report
Image Super-Resolution Urban100 - 8x upscaling ABPN SSIM 0.641 #5 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.

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