Research map / Learning theory and algorithms / Matrix and tensor methods
Recovery Analysis for Plug-and-Play Priors using the Restricted Eigenvalue Condition
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 |
|---|---|---|---|
| Use an artifact-removal prior instead of an AWGN denoiser in PnP (ablation) | PnP · BSD68, CS 10% | PSNR (dB): 25.06 -> 26.46 | Helped |
| Use an artifact-removal prior instead of an AWGN denoiser in PnP (ablation) | PnP · Set11, CS 10% | PSNR (dB): 27.76 -> 28.98 | Helped |
| Use an artifact-removal prior instead of an AWGN denoiser in PnP (ablation) | PnP · CS-MRI, CS 10% | PSNR (dB): 34.56 -> 35.21 | Helped |
| Use an artifact-removal prior instead of an AWGN denoiser in PnP (ablation) | PnP · CelebA HQ, CS 10% | PSNR (dB): 35.61 -> 39.19 | Helped |
| Use RED rather than PnP with the AWGN denoiser | PnP/RED · BSD68 and Set11 CS | PSNR (dB): 30.31 vs 30.20; 35.06 vs 35.01 | No clear effect |
| Use PnP with an AR prior instead of the strongest listed baseline | CS recovery · CelebA HQ, CS 30% | PSNR (dB): 43.46 -> 48.66 | Helped |
Closest papers by meaning
- Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction (NeurIPS 2024 · similarity 0.90)
- Plug-and-Play image restoration with Stochastic deNOising REgularization (ICML 2024 · similarity 0.89)
- Learning Cocoercive Conservative Denoisers via Helmholtz Decomposition for Poisson Imaging Inverse Problems (NeurIPS 2025 · similarity 0.89)
- A Restoration Network as an Implicit Prior (ICLR 2024 · similarity 0.89)
- FiRe: Fixed-points of Restoration Priors for Solving Inverse Problems (CVPR 2025 · similarity 0.88)
- A Diffusion Model with State Estimation for Degradation-Blind Inverse Imaging (AAAI 2024 · 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.