Papers › Deblurring by Realistic Blurring
Deblurring by Realistic Blurring
Kaihao Zhang, Wenhan Luo, Yiran Zhong, Lin Ma, Bjorn Stenger, Wei Liu, Hongdong Li
Existing deep learning methods for image deblurring typically train models using pairs of sharp images and their blurred counterparts. However, synthetically blurring images do not necessarily model the genuine blurring process in real-world scenarios with sufficient accuracy. To address this problem, we propose a new method which combines two GAN models, i.e., a learning-to-Blur GAN (BGAN) and learning-to-DeBlur GAN (DBGAN), in order to learn a better model for image deblurring by primarily learning how to blur images. The first model, BGAN, learns how to blur sharp images with unpaired sharp and blurry image sets, and then guides the second model, DBGAN, to learn how to correctly deblur such images. In order to reduce the discrepancy between real blur and synthesized blur, a relativistic blur loss is leveraged. As an additional contribution, this paper also introduces a Real-World Blurred Image (RWBI) dataset including diverse blurry images. Our experiments show that the proposed method achieves consistently superior quantitative performance as well as higher perceptual quality on both the newly proposed dataset and the public GOPRO dataset.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Deblurring | GoPro | DBGAN | PSNR | 31.10 | #47 of 56 | Archive leaderboard | report |
| Deblurring | GoPro | DBGAN | SSIM | 0.9424 | #47 of 56 | Archive leaderboard | report |
| Deblurring | HIDE (trained on GOPRO) | DBGAN | PSNR (sRGB) | 28.94 | #24 of 26 | Archive leaderboard | report |
| Deblurring | HIDE (trained on GOPRO) | DBGAN | SSIM (sRGB) | 0.915 | #24 of 26 | Archive leaderboard | report |
| Image Deblurring | GoPro | DBGAN | PSNR | 31.10 | #44 of 55 | Archive leaderboard | report |
| Image Deblurring | GoPro | DBGAN | SSIM | 0.9424 | #44 of 55 | 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
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