Research map / Image generation / Image restoration
GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration
Naoki Murata, Koichi Saito, Chieh-Hsin Lai, Yuhta Takida, Toshimitsu Uesaka, Yuki Mitsufuji, Stefano Ermon
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 |
|---|---|---|---|
| Use GibbsDDRM instead of BlindDPS | Blind image deblurring · FFHQ 256×256 | LPIPS: 0.281 -> 0.115 | Improved |
| Use GibbsDDRM instead of MPRNet | Blind image deblurring · FFHQ 256×256 | PSNR: 27.23 -> 25.80 | Hurt |
| Use GibbsDDRM instead of BlindDPS | Blind image deblurring · AFHQ 256×256 | LPIPS: 0.338 -> 0.197 | Improved |
| Use GibbsDDRM instead of Unsupervised Dereverberation | Vocal dereverberation · Vocal dereverberation | FAD: 4.99 -> 4.21 | Improved |
| Use GibbsDDRM instead of Unsupervised Dereverberation | Vocal dereverberation · Vocal dereverberation | SI-SDR improvement: 0.37 -> 0.59 | Improved |
| Use GibbsDDRM instead of Unsupervised Dereverberation | Vocal dereverberation · Vocal dereverberation | SRMR: 7.94 -> 8.40 | Improved |
| Use Music Enhancement instead of processing the wet signal unchanged | Vocal dereverberation · Vocal dereverberation | SI-SDR improvement: -- -> -23.9 | Hurt |
Later papers that compared with this method
1 later accepted paper reports GibbsDDRM as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- CL-DPS: A Contrastive Learning Approach to Blind Nonlinear Inverse Problem Solving via Diffusion Posterior Sampling (ICLR 2026 · better on 7 of 7 shared results)
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
- Unleashing the Denoising Capability of Diffusion Prior for Solving Inverse Problems (NeurIPS 2024 · similarity 0.90)
- A Diffusion Model with State Estimation for Degradation-Blind Inverse Imaging (AAAI 2024 · similarity 0.90)
- A Mixture-Based Framework for Guiding Diffusion Models (ICML 2025 · similarity 0.90)
- A Variational Perspective on Solving Inverse Problems with Diffusion Models (ICLR 2024 · similarity 0.90)
- Divide-and-Conquer Posterior Sampling for Denoising Diffusion priors (NeurIPS 2024 · similarity 0.90)
- Adapt and Diffuse: Sample-adaptive Reconstruction via Latent Diffusion Models (ICML 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.
