Papers › Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image...
Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Training
Dongwon Park, Dong Un Kang, Jisoo Kim, Se Young Chun
Multi-scale (MS) approaches have been widely investigated for blind single image / video deblurring that sequentially recovers deblurred images in low spatial scale first and then in high spatial scale later with the output of lower scales. MS approaches have been effective especially for severe blurs induced by large motions in high spatial scale since those can be seen as small blurs in low spatial scale. In this work, we investigate alternative approach to MS, called multi-temporal (MT) approach, for non-uniform single image deblurring. We propose incremental temporal training with constructed MT level dataset from time-resolved dataset, develop novel MT-RNNs with recurrent feature maps, and investigate progressive single image deblurring over iterations. Our proposed MT methods outperform state-of-the-art MS methods on the GoPro dataset in PSNR with the smallest number of parameters.
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 | MT-RNN | PSNR | 31.15 | #45 of 56 | Archive leaderboard | report |
| Deblurring | GoPro | MT-RNN | SSIM | 0.945 | #45 of 56 | Archive leaderboard | report |
| Deblurring | HIDE (trained on GOPRO) | MT-RNN | PSNR (sRGB) | 29.15 | #21 of 26 | Archive leaderboard | report |
| Deblurring | HIDE (trained on GOPRO) | MT-RNN | Params (M) | 2.6 | #21 of 26 | Archive leaderboard | report |
| Deblurring | HIDE (trained on GOPRO) | MT-RNN | SSIM (sRGB) | 0.918 | #21 of 26 | Archive leaderboard | report |
| Image Deblurring | GoPro | MT-RNN | PSNR | 31.15 | #42 of 55 | Archive leaderboard | report |
| Image Deblurring | GoPro | MT-RNN | SSIM | 0.945 | #42 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.
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