Research map / Image generation / Image restoration
DiffBIR: Toward Blind Image Restoration with Generative Diffusion Prior
Xinqi Lin, Jingwen He, Ziyan Chen, Zhaoyang Lyu, Bo Dai, Fanghua Yu, Yu Qiao, Wanli Ouyang, Chao Dong
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 a restoration module stage before the diffusion generator (two-stage pipeline) (ablation) | DiffBIR · RealSRSet | MUSIQ: 62.5683 -> 64.7319 | Improved |
| add restoration module (ablation) | DiffBIR · ImageNet-Val-1k | PSNR: 22.8481 -> 23.0078 | Improved |
| use IRControlNet instead of ControlNet (ablation) | DiffBIR · ImageNet-Val-1k | PSNR: 22.2874 -> 24.2534 | Improved |
| use wide-range degradation model instead of Real-ESRGAN degradation for condition images (ablation) | DiffBIR · RealSRSet | CLIP-IQA: 0.6936 -> 0.7075 | Improved |
| raise restoration guidance scale from 0 to 1 (ablation) | DiffBIR · DIV2K-Val BSR | PSNR: 20.5824 -> 21.9154 | Improved |
| raise restoration guidance scale from 0 to 1 (ablation) | DiffBIR · DIV2K-Val BSR | MUSIQ: 73.1019 -> 61.1476 | Hurt |
| use control concat or SFT variants instead of add-on IRControlNet (ablation) | IRControlNet · ImageNet1k-Val | PSNR vs MANIQA: PSNR 22.9865 -> 23.0449; MANIQA 0.2689 -> 0.2567 | Mixed |
| DiffBIR (s=0) vs GAN-based methods on perceptual PSNR on DIV2K-Val | DiffBIR · DIV2K-Val BSR | PSNR: 21.4531 -> 20.5824 | Hurt |
| use generic-image diffusion prior (not trained on faces) for blind face restoration | DiffBIR · LFW-Test | FID (ref. FFHQ): 41.5814 -> 40.9065 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- DifFace — DifFace: Blind Face Restoration With Diffused Error Contraction (TPAMI 2024) · better on 1 of 1 shared result
- PGDiff — PGDiff: Guiding Diffusion Models for Versatile Face Restoration via Partial Guidance (NeurIPS 2023) · 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
- Taming Generative Diffusion Prior for Universal Blind Image Restoration (NeurIPS 2024 · similarity 0.90)
- A Modular Conditional Diffusion Framework for Image Reconstruction (NeurIPS 2024 · similarity 0.89)
- Blind Image Restoration via Fast Diffusion Inversion (NeurIPS 2024 · similarity 0.89)
- Improving Diffusion-Based Image Restoration with Error Contraction and Error Correction (AAAI 2024 · similarity 0.88)
- Restoration by Generation with Constrained Priors (CVPR 2024 · similarity 0.88)
- Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration (ICLR 2025 · similarity 0.88)
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.
