AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Solving Diffusion Inverse Problems with Restart Posterior Sampling

Bilal Ahmed, Joseph Makin

ECCV 2026 · Image generation › Fast diffusion sampling · approach: Diffusion posterior sampling · 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 restarts to the conditioned ODE (RePS) versus plain ODE or SDE (ablation)RePS · FFHQ Gaussian deblurPSNR and LPIPS across NFEsImproved
use plain conditioned ODE without restart at high NFE (ablation)conditioned ODE · FFHQ Gaussian deblurPSNR and LPIPSHurt
increase conditioned ODE steps between restarts up to about 5 steps (ablation)RePS · inverse problems, 1000 NFEsPSNRImproved
increase ODE steps between restarts beyond about 20 (ablation)RePS · inverse problems, 1000 NFEsLPIPSHurt
use multiple conditioned ODE steps per restart instead of one (DiffPIR-style) (ablation)RePS · linear inverse problemsPSNR/LPIPSImproved
replace DAPS two-stage conditioning with conditioned ODE (RePS)RePS vs DAPS · linear and nonlinear tasksPSNR/LPIPSMixed
RePS vs DAPS on motion deblurring across NFEsRePS · motion deblurringPSNR and LPIPSImproved
RePS vs DAPS sampling timeRePS · all taskstime per imageNo 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