Papers › Scale-recurrent Network for Deep Image Deblurring

Scale-recurrent Network for Deep Image Deblurring

6 Feb 2018CVPR 2018 6arXiv:1802.01770archive 2025-07-28

Xin Tao, Hongyun Gao, Yi Wang, Xiaoyong Shen, Jue Wang, Jiaya Jia

In single image deblurring, the "coarse-to-fine" scheme, i.e. gradually restoring the sharp image on different resolutions in a pyramid, is very successful in both traditional optimization-based methods and recent neural-network-based approaches. In this paper, we investigate this strategy and propose a Scale-recurrent Network (SRN-DeblurNet) for this deblurring task. Compared with the many recent learning-based approaches in [25], it has a simpler network structure, a smaller number of parameters and is easier to train. We evaluate our method on large-scale deblurring datasets with complex motion. Results show that our method can produce better quality results than state-of-the-arts, both quantitatively and qualitatively.

PaperPDFConference PDFCode

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

Code

IMAC-projects/Deblurring-PyTorch mentioned on GitHubpytorch report
IMAC-projects/SRN-Deblurring-PyTorch mentioned 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

DeblurringImage DeblurringImage RelightingSingle Image Deblurring

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Deblurring GoPro SRN SSIM 0.9342 #56 of 56 Archive leaderboard report
Deblurring HIDE (trained on GOPRO) SRN PSNR (sRGB) 28.36 #25 of 26 Archive leaderboard report
Deblurring HIDE (trained on GOPRO) SRN Params (M) 8.06 #25 of 26 Archive leaderboard report
Deblurring HIDE (trained on GOPRO) SRN SSIM (sRGB) 0.915 #25 of 26 Archive leaderboard report
Deblurring RSBlur SRN-Deblur Average PSNR 32.53 #12 of 12 Archive leaderboard report
Deblurring RealBlur-J SRN PSNR (sRGB) 31.38 #16 of 17 Archive leaderboard report
Deblurring RealBlur-J SRN Params(M) 8.06 #16 of 17 Archive leaderboard report
Deblurring RealBlur-J SRN SSIM (sRGB) 0.909 #16 of 17 Archive leaderboard report
Deblurring RealBlur-J (trained on GoPro) SRN PSNR (sRGB) 28.56 #12 of 15 Archive leaderboard report
Deblurring RealBlur-R SRN PSNR (sRGB) 38.65 #15 of 17 Archive leaderboard report
Deblurring RealBlur-R SRN Params 8.06 #15 of 17 Archive leaderboard report
Deblurring RealBlur-R SRN SSIM (sRGB) 0.965 #15 of 17 Archive leaderboard report
Deblurring RealBlur-R (trained on GoPro) SRN SSIM (sRGB) 0.947 #14 of 19 Archive leaderboard report
Image Deblurring GoPro SRN Params (M) 8.06 #55 of 55 Archive leaderboard report
Image Deblurring GoPro SRN SSIM 0.9342 #55 of 55 Archive leaderboard report
Image Relighting VIDIT’20 validation set SRN LPIPS 0.4319 #5 of 5 Archive leaderboard report
Image Relighting VIDIT’20 validation set SRN MPS 0.5670 #5 of 5 Archive leaderboard report
Image Relighting VIDIT’20 validation set SRN PSNR 16.94 #5 of 5 Archive leaderboard report
Image Relighting VIDIT’20 validation set SRN Runtime(s) 0.87 #5 of 5 Archive leaderboard report
Image Relighting VIDIT’20 validation set SRN SSIM 0.5660 #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