Scale-recurrent Network for Deep Image Deblurring
Xin Tao, Hongyun Gao, Yi Wang, Xiaoyong Shen, Jue Wang, Jiaya Jia
Code Available — Be the first to reproduce this paper.
ReproduceCode
Abstract
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.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| GoPro | SRN | SSIM | 0.93 | — | Unverified |
| HIDE (trained on GOPRO) | SRN | PSNR (sRGB) | 28.36 | — | Unverified |
| RealBlur-J | SRN | PSNR (sRGB) | 31.38 | — | Unverified |
| RealBlur-J (trained on GoPro) | SRN | PSNR (sRGB) | 28.56 | — | Unverified |
| RealBlur-R | SRN | PSNR (sRGB) | 38.65 | — | Unverified |
| RealBlur-R (trained on GoPro) | SRN | SSIM (sRGB) | 0.95 | — | Unverified |
| RSBlur | SRN-Deblur | Average PSNR | 32.53 | — | Unverified |