Research map / Image generation / Image restoration
Deep Image Deblurring: A Survey
Kaihao Zhang, Wenqi Ren, Wenhan Luo, Wei‐Sheng Lai, Björn Stenger, Ming–Hsuan Yang, Hongdong Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add perceptual and GAN loss to L2 loss (ablation) | single image deblurring network · Single image deblurring | PSNR: 26.78 -> 27.20 | Improved |
| add perceptual and GAN loss to L1 loss (ablation) | single image deblurring network · Single image deblurring | PSNR: 26.24 -> 26.89 | Improved |
| use RaGAN instead of GAN with L2 + perceptual (ablation) | single image deblurring network · Single image deblurring | PSNR: 27.20 -> 27.09 | Hurt |
| use L2 instead of L1 pixel loss (ablation) | single image deblurring network · Single image deblurring | PSNR: 26.24 -> 26.78 | Improved |
| train on RealBlur-J + BSD-B + GoPro instead of RealBlur-J only (ablation) | SRN · RealBlur-J test | PSNR: 31.02 -> 31.37 | Improved |
| train on GoPro only instead of in-domain RealBlur-J (ablation) | SRN · RealBlur-J test | PSNR: 31.02 -> 28.56 | Hurt |
| provide ground-truth blur kernels (non-blind instead of blind) | USRNet vs SRN · Non-blind GoPro | PSNR: 34.78 -> 36.51 | Improved |
| use multi-scale architecture for UHD deblurring | SRN vs DeblurGAN · UHD image deblurring | PSNR: 19.25 -> 21.25 | Improved |
| use video deblurring network instead of single image network | Pan et al. vs Tao et al. · DVD | PSNR: 29.97 -> 32.13 | Improved |
| use multi-scale scale-recurrent net instead of conditional GAN | Tao et al. vs Kupyn et al. · GoPro | PSNR: 28.70 -> 30.26 | Improved |
Closest papers by meaning
- Deep Semantic Face Deblurring (CVPR 2018 · similarity 0.92)
- Learning a Discriminative Prior for Blind Image Deblurring (CVPR 2018 · similarity 0.92)
- Exploiting Semantics for Face Image Deblurring (IJCV 2020 · similarity 0.92)
- Deblurring by Realistic Blurring (CVPR 2020 · similarity 0.91)
- Deep Wiener Deconvolution: Wiener Meets Deep Learning for Image Deblurring (NeurIPS 2020 · similarity 0.91)
- Blur2Blur: Blur Conversion for Unsupervised Image Deblurring on Unknown Domains (CVPR 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
