Research map / Image generation / Image restoration
Explore Image Deblurring via Encoded Blur Kernel Space
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use the encoded blur kernel space to retrieve blur kernels across domains | Blind image deblurring · REDS4 and GOPRO | PSNR: 34.35; 30.67; 31.38; 35.13 | Helped |
| Replace original SRN-Deblur training pairs with blur-swapped pairs (ablation) | SRN-Deblur · REDS and GOPRO | PSNR: 30.70 -> 29.43; 30.20 -> 28.49 | Hurt |
| Add encoded REDS blur kernels to imgaug training data (ablation) | SRN-Deblur · FFHQ with REDS test blur | PSNR: 24.22 -> 28.37 | Helped |
| Add encoded REDS blur kernels to imgaug training data (ablation) | SRN-Deblur · FFHQ with GOPRO test blur | PSNR: 22.96 -> 23.92 | Helped |
| Add encoded REDS blur kernels to imgaug training data (ablation) | SRN-Deblur · FFHQ with imgaug test blur | PSNR: 28.64 -> 28.30 | Hurt |
| Use the encoded blur kernel prior rather than uniform convolution or bicubic-downsampling kernels (ablation) | StyleGAN-manifold face deblurring · In-the-wild blurry faces | Loss convergence | Helped |
| Use the encoded kernel prior instead of convolutional or bicubic kernels (ablation) | StyleGAN-manifold face deblurring · In-the-wild blurry faces | Deblurring quality | Helped |
Closest papers by meaning
- Prior and Prediction Inverse Kernel Transformer for Single Image Defocus Deblurring (AAAI 2024 · similarity 0.89)
- DeblurDiff: Real-Word Image Deblurring with Generative Diffusion Models (NeurIPS 2025 · similarity 0.88)
- Blur2Blur: Blur Conversion for Unsupervised Image Deblurring on Unknown Domains (CVPR 2024 · similarity 0.87)
- Parameterized Blur Kernel Prior Learning for Local Motion Deblurring (CVPR 2025 · similarity 0.87)
- Cross-Scale Self-Supervised Blind Image Deblurring via Implicit Neural Representation (NeurIPS 2024 · similarity 0.87)
- Unsupervised Blind Image Deblurring Based on Self-Enhancement (CVPR 2024 · similarity 0.86)
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.