Papers › Deep Back-Projection Networks for Single Image Super-resolution

Deep Back-Projection Networks for Single Image Super-resolution

4 Apr 2019arXiv:1904.05677archive 2025-07-28

Muhammad Haris, Greg Shakhnarovich, Norimichi Ukita

Previous feed-forward architectures of recently proposed deep super-resolution networks learn the features of low-resolution inputs and the non-linear mapping from those to a high-resolution output. However, this approach does not fully address the mutual dependencies of low- and high-resolution images. We propose Deep Back-Projection Networks (DBPN), the winner of two image super-resolution challenges (NTIRE2018 and PIRM2018), that exploit iterative up- and down-sampling layers. These layers are formed as a unit providing an error feedback mechanism for projection errors. We construct mutually-connected up- and down-sampling units each of which represents different types of low- and high-resolution components. We also show that extending this idea to demonstrate a new insight towards more efficient network design substantially, such as parameter sharing on the projection module and transition layer on projection step. The experimental results yield superior results and in particular establishing new state-of-the-art results across multiple data sets, especially for large scaling factors such as 8x.

PaperPDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

Code

alterzero/DBPN-Pytorch mentioned on GitHubpytorchMIT report
lizatish/My_CNN mentioned on GitHubpytorch report
shnhrtkyk/satellite-super-resolution mentioned on GitHubpytorch report
lyqcom/dbpn mindspore 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 BSDS100 - 2x upscaling DBPN-RES-MR64-3 PSNR 32.31 #1 of 2 Archive leaderboard report
Image Super-Resolution BSDS100 - 2x upscaling DBPN-RES-MR64-3 SSIM 0.901 #1 of 2 Archive leaderboard report
Image Super-Resolution BSDS100 - 4x upscaling DBPN-RES-MR64-3 PSNR 27.82 #1 of 1 Archive leaderboard report
Image Super-Resolution BSDS100 - 4x upscaling DBPN-RES-MR64-3 SSIM 0.744 #1 of 1 Archive leaderboard report
Image Super-Resolution BSDS100 - 8x upscaling DBPN-RES-MR64-3 PSNR 25.05 #1 of 1 Archive leaderboard report
Image Super-Resolution BSDS100 - 8x upscaling DBPN-RES-MR64-3 SSIM 0.607 #1 of 1 Archive leaderboard report
Image Super-Resolution Manga109 - 2x upscaling DBPN-RES-MR64-3 PSNR 39.28 #15 of 21 Archive leaderboard report
Image Super-Resolution Manga109 - 2x upscaling DBPN-RES-MR64-3 SSIM 0.977 #15 of 21 Archive leaderboard report
Image Super-Resolution Manga109 - 4x upscaling DBPN-RES-MR64-3 PSNR 31.74 #23 of 50 Archive leaderboard report
Image Super-Resolution Manga109 - 4x upscaling DBPN-RES-MR64-3 SSIM 0.921 #23 of 50 Archive leaderboard report
Image Super-Resolution Manga109 - 8x upscaling DBPN-RES-MR64-3 PSNR 25.71 #1 of 5 Archive leaderboard report
Image Super-Resolution Manga109 - 8x upscaling DBPN-RES-MR64-3 SSIM 0.813 #1 of 5 Archive leaderboard report
Image Super-Resolution Set14 - 2x upscaling DBPN-RES-MR64-3 PSNR 34.09 #17 of 35 Archive leaderboard report
Image Super-Resolution Set14 - 2x upscaling DBPN-RES-MR64-3 SSIM 0.921 #17 of 35 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling DBPN-RES-MR64-3 PSNR 29.03 #28 of 104 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling DBPN-RES-MR64-3 SSIM 0.791 #28 of 104 Archive leaderboard report
Image Super-Resolution Set14 - 8x upscaling DBPN-RES-MR64-3 PSNR 25.41 #1 of 7 Archive leaderboard report
Image Super-Resolution Set14 - 8x upscaling DBPN-RES-MR64-3 SSIM 0.657 #1 of 7 Archive leaderboard report
Image Super-Resolution Set5 - 2x upscaling DBPN-RES-MR64-3 PSNR 38.08 #25 of 41 Archive leaderboard report
Image Super-Resolution Set5 - 2x upscaling DBPN-RES-MR64-3 SSIM 0.96 #25 of 41 Archive leaderboard report
Image Super-Resolution Set5 - 8x upscaling DBPN-RES-MR64-3 PSNR 27.51 #2 of 8 Archive leaderboard report
Image Super-Resolution Set5 - 8x upscaling DBPN-RES-MR64-3 SSIM 0.793 #2 of 8 Archive leaderboard report
Image Super-Resolution Urban100 - 2x upscaling DBPN-RES-MR64-3 PSNR 32.92 #18 of 29 Archive leaderboard report
Image Super-Resolution Urban100 - 2x upscaling DBPN-RES-MR64-3 SSIM 0.935 #18 of 29 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling DBPN-RES-MR64-3 PSNR 27.08 #21 of 65 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling DBPN-RES-MR64-3 SSIM 0.814 #21 of 65 Archive leaderboard report
Image Super-Resolution Urban100 - 8x upscaling DBPN-RES-MR64-3 PSNR 23.2 #2 of 5 Archive leaderboard report
Image Super-Resolution Urban100 - 8x upscaling DBPN-RES-MR64-3 SSIM 0.652 #2 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