AI Paper Atlas

Research map / Optimization / Optimizers

Taming Score-Based Denoisers in ADMM: A Convergent Plug-and-Play Framework

Rajesh Shrestha, Xiao Fu

ICLR 2026 · Optimization › Optimizers · approach: Surrogate losses and robust solvers · 1 citations (OpenAlex)

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 changedWhereMeasuredEffect
use AC-DC tweedie denoiser instead of DAPSADMM-PnP · FFHQ phase retrievalPSNR (dB): 26.707 -> 27.944Improved
use AC-DC tweedie denoiser instead of DPSADMM-PnP · FFHQ phase retrievalPSNR (dB): 11.627 -> 27.944Improved
use tweedie instead of ODE variantAC-DC denoiser · FFHQ 4x super-resolutionPSNR (dB): 29.991 -> 30.439Improved
use tweedie instead of ODE variantAC-DC denoiser · FFHQ random inpaintingLPIPS: 0.095 -> 0.122Hurt
add AC-DC denoiser vs DCDP on box inpaintingADMM-PnP · FFHQ box inpaintingPSNR (dB): 25.230 -> 24.025Hurt
add DC (Langevin) iterations, J>0 instead of J=0 (ablation)AC-DC denoiser · phase retrievalvisual qualityImproved
use AC-DC tweedie instead of DPSADMM-PnP · ImageNet motion deblurringPSNR (dB): 19.613 -> 27.149Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy