Research map / Learning theory and algorithms / Matrix and tensor methods
Block Coordinate Regularization by Denoising
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 BC-RED instead of full-gradient RED with BM3D prior | RED (BM3D) · Radon, 30 dB | SNR: 21.55 -> 21.56 | No clear effect |
| Use BC-RED instead of full-gradient RED with BM3D prior | RED (BM3D) · Radon, 40 dB | SNR: 25.24 -> 25.16 | Hurt |
| Use BC-RED instead of full-gradient RED with DnCNN* prior | RED (DnCNN*) · Random, 30 dB | SNR: 26.53 -> 26.60 | Helped |
| Use BC-RED instead of full-gradient RED with DnCNN* prior | RED (DnCNN*) · Fourier, 40 dB | SNR: 30.32 -> 30.39 | Helped |
| Use randomized-epoch block selection rather than full-gradient RED (ablation) | BC-RED with DnCNN* · Radon, 30 dB | iterations to accuracy 10^-10: 190 -> 104 | Helped |
| Increase τ for the proximal-operator denoiser (ablation) | BC-RED solving TV-regularized least squares · Fourier, 40 dB | relative objective gap | Helped |
| Use randomized-epoch block selection rather than i.i.d. block selection (ablation) | BC-RED · Radon, 30 dB | convergence rate | Helped |
Closest papers by meaning
- Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction (NeurIPS 2024 · similarity 0.85)
- MAP Estimation with Denoisers: Convergence Rates and Guarantees (NeurIPS 2025 · similarity 0.85)
- Plug-and-Play image restoration with Stochastic deNOising REgularization (ICML 2024 · similarity 0.85)
- Diffusion Priors for Variational Likelihood Estimation and Image Denoising (NeurIPS 2024 · similarity 0.84)
- A Variational Perspective on Solving Inverse Problems with Diffusion Models (ICLR 2024 · similarity 0.84)
- Prior Mismatch and Adaptation in PnP-ADMM with a Nonconvex Convergence Analysis (ICML 2024 · similarity 0.84)
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.