Research map / Image generation / Image restoration
Denoising Diffusion Restoration Models
Read the paperCheck 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 |
|---|---|---|---|
| DDRM spectral-space conditional diffusion sampling with 20 NFEs vs RED | unsupervised inverse solvers · ImageNet 4x SR noiseless | PSNR: 26.08 -> 26.55 | Helped |
| DDRM vs SNIPS | diffusion-based inverse solvers · ImageNet deblurring noiseless | KID: 0.49 vs 0.71 | Hurt |
| DDRM vs DGP under measurement noise | unsupervised inverse solvers · ImageNet deblurring sigma=0.05 | PSNR: 21.20 -> 25.45 | Helped |
| use class-conditional diffusion model (DDRM-CC) | DDRM · ImageNet 4x SR sigma=0.05 | KID: 12.43 -> 10.82 | Helped |
| increase eta_b from 0.7 to 1.0 (ablation) | DDRM eta=0.7 · ImageNet deblurring sigma=0.05 | KID: 16.27 -> 11.65 | Helped |
| increase eta from 0.7 to 1.0 (ablation) | DDRM eta_b=1.0 · ImageNet deblurring sigma=0.05 | KID: 11.65 -> 37.84 | Hurt |
| 100 timesteps instead of 20 (ablation) | DDRM · ImageNet | PSNR/KID | No clear effect |
Closest papers by meaning
- A Variational Perspective on Solving Inverse Problems with Diffusion Models (ICLR 2024 · similarity 0.93)
- Residual Denoising Diffusion Models (CVPR 2024 · similarity 0.91)
- Diffusion Priors for Variational Likelihood Estimation and Image Denoising (NeurIPS 2024 · similarity 0.91)
- Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration (ICLR 2025 · similarity 0.91)
- Improving Diffusion-Based Image Restoration with Error Contraction and Error Correction (AAAI 2024 · similarity 0.91)
- Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise (NeurIPS 2024 · similarity 0.91)
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.