Research map / Learning theory and algorithms / Matrix and tensor methods
Convergent Bregman Plug-and-Play Image Restoration for Poisson Inverse Problems
Samuel Hurault, Ulugbek Kamilov, Arthur Leclaire, Nicolas Papadakis
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 |
|---|---|---|---|
| constrain denoiser to gradient form (B-DRUNet) instead of unconstrained DRUNet | DRUNet · CBSD68 Inverse Gamma denoising, gamma=10 | PSNR (dB): 28.42 -> 28.38 | No clear effect |
| constrain denoiser to gradient form (B-DRUNet) instead of unconstrained DRUNet | DRUNet · CBSD68 Inverse Gamma denoising, gamma=25 | PSNR (dB): 30.91 -> 30.88 | No clear effect |
| constrain denoiser to gradient form (B-DRUNet) instead of unconstrained DRUNet | DRUNet · CBSD68 Inverse Gamma denoising, gamma=50 | PSNR (dB): 32.80 -> 32.76 | No clear effect |
| constrain denoiser to gradient form (B-DRUNet) instead of unconstrained DRUNet | DRUNet · CBSD68 Inverse Gamma denoising, gamma=100 | PSNR (dB): 34.76 -> 34.74 | No clear effect |
| constrain denoiser to gradient form (B-DRUNet) instead of unconstrained DRUNet | DRUNet · CBSD68 Inverse Gamma denoising, gamma=200 | PSNR (dB): 36.79 -> 36.71 | No clear effect |
| B-PnP instead of B-RED | B-RED · Poisson deblurring, motion kernel, alpha=40 | PSNR (dB): 23.01 -> 22.96 | No clear effect |
| B-PnP instead of B-RED | B-RED · Poisson deblurring, Gaussian kernel, alpha=60 | PSNR (dB): 24.50 -> 24.51 | No clear effect |
Closest papers by meaning
- Learning Cocoercive Conservative Denoisers via Helmholtz Decomposition for Poisson Imaging Inverse Problems (NeurIPS 2025 · similarity 0.90)
- Plug-and-Play image restoration with Stochastic deNOising REgularization (ICML 2024 · similarity 0.89)
- PnP-Flow: Plug-and-Play Image Restoration with Flow Matching (ICLR 2025 · similarity 0.88)
- Prior Mismatch and Adaptation in PnP-ADMM with a Nonconvex Convergence Analysis (ICML 2024 · similarity 0.88)
- Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction (NeurIPS 2024 · similarity 0.88)
- Equivariant Plug-and-Play Image Reconstruction (CVPR 2024 · similarity 0.87)
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.
