Research map / Image generation / Image restoration
Learning Deblurring Texture Prior from Unpaired Data with Diffusion Model
Chengxu Liu, Lu Qi, Jinshan Pan, Xueming Qian, Ming-Hsuan Yang
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 diffusion model texture prior generation (ablation) | TP-Diff · GoPro | PSNR: -1.67 dB | Improved |
| add Texture Prior Encoder (ablation) | TP-Diff · GoPro | PSNR: -0.77 dB | Improved |
| add TTformer (ablation) | TP-Diff · GoPro | PSNR: -0.94 dB | Improved |
| use TPE instead of latent encoder (ablation) | TP-Diff · GoPro | PSNR: 27.74 -> 28.13 | Improved |
| combine enhancement and transfer parts in TPE (ablation) | TP-Diff · GoPro | PSNR: 27.73 -> 28.13 | Improved |
| learn texture prior in feature space instead of RGB space (ablation) | TP-Diff · GoPro | PSNR: 26.95 -> 28.13 | Improved |
| random sampling vs single sharp image reuse (ablation) | TP-Diff · GoPro | PSNR: 27.94 -> 28.13 | Improved |
| cluster-guided sampling instead of random (ablation) | TP-Diff · GoPro | PSNR: 28.13 -> 28.18 | No clear effect |
| increase memory size N from 128 to 256 (ablation) | TP-Diff · GoPro | PSNR: 27.99 -> 28.13 | Improved |
| increase memory size N from 256 to 512 (ablation) | TP-Diff · GoPro | PSNR: 28.13 -> 28.19 | No clear effect |
| use FM-MSA adaptive filtering instead of no filtering (ablation) | TP-Diff · GoPro | PSNR: 27.81 -> 28.13 | Improved |
| use FM-MSA instead of vanilla filtering (ablation) | TP-Diff · GoPro | PSNR: 27.93 -> 28.13 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- U-GAT-IT — U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation (ICLR 2020) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- DeblurDiff: Real-Word Image Deblurring with Generative Diffusion Models (NeurIPS 2025 · similarity 0.88)
- Learning Diffusion Texture Priors for Image Restoration (CVPR 2024 · similarity 0.88)
- BlurDM: A Blur Diffusion Model for Image Deblurring (NeurIPS 2025 · similarity 0.88)
- Residual Diffusion Deblurring Model for Single Image Defocus Deblurring (AAAI 2025 · similarity 0.87)
- Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training (AAAI 2025 · similarity 0.87)
- Blur2Blur: Blur Conversion for Unsupervised Image Deblurring on Unknown Domains (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.
