Papers › DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks

DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks

19 Nov 2017CVPR 2018 6arXiv:1711.07064archive 2025-07-28

Orest Kupyn, Volodymyr Budzan, Mykola Mykhailych, Dmytro Mishkin, Jiri Matas

We present DeblurGAN, an end-to-end learned method for motion deblurring. The learning is based on a conditional GAN and the content loss . DeblurGAN achieves state-of-the art performance both in the structural similarity measure and visual appearance. The quality of the deblurring model is also evaluated in a novel way on a real-world problem -- object detection on (de-)blurred images. The method is 5 times faster than the closest competitor -- DeepDeblur. We also introduce a novel method for generating synthetic motion blurred images from sharp ones, allowing realistic dataset augmentation. The model, code and the dataset are available at https://github.com/KupynOrest/DeblurGAN

PaperPDFConference PDFCode

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

Code

13 repositories listed; official and paper-mentioned ones first.

KupynOrest/DeblurGAN officialmentioned in papermentioned on GitHubpytorch report
The-GAN-g/DeblurGAN mentioned on GitHubpytorch report
anastasiia-kornilova/MMDF mentioned on GitHubtf report
au1206/Enhance-GAN mentioned on GitHub report
fabriziocacicia/DeblurGAN-TF2.0 mentioned on GitHubtf report
fatalfeel/DeblurGAN mentioned on GitHubpytorch report
lycutter/deblur_sr_gan mentioned on GitHubpytorch report
pablodz/deblurgan mentioned on GitHubpytorch report
pgarz/runway_exercise mentioned on GitHubpytorch report
testestzxcv/DeblurGAN 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

DeblurringObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Deblurring REDS DeblurGAN Average PSNR 24.09 #3 of 3 Archive leaderboard report
Deblurring RealBlur-J (trained on GoPro) DeblurGAN SSIM (sRGB) 0.834 #15 of 15 Archive leaderboard report
Deblurring RealBlur-R (trained on GoPro) DeblurGAN SSIM (sRGB) 0.903 #18 of 19 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