Research map / Optimization / Optimizers
Taming Score-Based Denoisers in ADMM: A Convergent Plug-and-Play Framework
Rajesh Shrestha, Xiao Fu
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 AC-DC tweedie denoiser instead of DAPS | ADMM-PnP · FFHQ phase retrieval | PSNR (dB): 26.707 -> 27.944 | Improved |
| use AC-DC tweedie denoiser instead of DPS | ADMM-PnP · FFHQ phase retrieval | PSNR (dB): 11.627 -> 27.944 | Improved |
| use tweedie instead of ODE variant | AC-DC denoiser · FFHQ 4x super-resolution | PSNR (dB): 29.991 -> 30.439 | Improved |
| use tweedie instead of ODE variant | AC-DC denoiser · FFHQ random inpainting | LPIPS: 0.095 -> 0.122 | Hurt |
| add AC-DC denoiser vs DCDP on box inpainting | ADMM-PnP · FFHQ box inpainting | PSNR (dB): 25.230 -> 24.025 | Hurt |
| add DC (Langevin) iterations, J>0 instead of J=0 (ablation) | AC-DC denoiser · phase retrieval | visual quality | Improved |
| use AC-DC tweedie instead of DPS | ADMM-PnP · ImageNet motion deblurring | PSNR (dB): 19.613 -> 27.149 | Improved |
Closest papers by meaning
- Noise Conditional Variational Score Distillation (ICML 2025 · similarity 0.89)
- Exact Posterior Score Estimation for Solving Linear Inverse Problems (NeurIPS 2026 · similarity 0.88)
- Prior Mismatch and Adaptation in PnP-ADMM with a Nonconvex Convergence Analysis (ICML 2024 · similarity 0.88)
- O(d/T) Convergence Theory for Diffusion Probabilistic Models under Minimal Assumptions (ICLR 2025 · similarity 0.88)
- Interpreting and Improving Diffusion Models from an Optimization Perspective (ICML 2024 · similarity 0.87)
- MAP Estimation with Denoisers: Convergence Rates and Guarantees (NeurIPS 2025 · 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.
