AI Paper Atlas

Research map / Image generation / Image restoration

Provably Accelerated Imaging with Restarted Inertia and Score-based Image Priors

Marien Renaud, Julien Hermant, Deliang Wei, Yu Sun

ICLR 2026 · Image generation › Image restoration · approach: Inverse imaging with learned priors · 2 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
add restarted inertia to REDRED-GM / RED-Prox · Linear inverse problems (deblurring, inpainting, SISR, MRI)gradient-norm decay per iteration: 3 -> 5 orders of magnitude within 200 iterations (deblurring)Improved
add restarted inertia to REDRED · MRIiterations to reach same PSNR: about five times fasterImproved
add restarted inertia to REDRED-GM · Rician denoising CBSD10runtime to comparable PSNR: 160 ms vs roughly ten times longerImproved
add restarted inertia to REDRED-GM / RED-Prox · Inverse scattering 1024x1024runtime: 20 min vs 480 min (still blurred)Improved
add restarted inertia to REDRED · Linear inverse problemsPSNRNo clear effect
restart mechanism with inertia theta (ablation)RISP · Linear inverse problemsrobustness to inertia parameterNo clear effect

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