AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Dual Ascent Diffusion for Inverse Problems

Minseo Kim, Axel Levy, Gordon Wetzstein

CVPR 2026 · Image generation › Fast diffusion sampling · approach: Diffusion posterior sampling

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 dual variable together with noising step (DDiff vs DDiff-HQS) (ablation)DDiff · FFHQ 256 Super-Resolution 4xLPIPS: 0.369 -> 0.199Improved
add dual variable without noising step (Diff-PnP-ADMM vs Diff-PnP-HQS) (ablation)Diff-PnP-HQS · FFHQ 256 Gaussian DeblurringPSNR: 5.82 -> 6.18 PSNR, LPIPS 0.858 -> 0.820Hurt
add dual variable alone without noising on super-resolution (ablation)Diff-PnP-HQS · FFHQ 256 Super-Resolution 4xLPIPS: 0.535 -> 0.572Hurt
add noising step (with dual variable) (ablation)Diff-PnP-ADMM · FFHQ 256 Super-Resolution 4xLPIPS: 0.572 -> 0.199Improved
replace DAPS-style MCMC with dual ascent at same NFEsDDiff · FFHQ, LPIPS vs timeLPIPS and sampling timeImproved
use DDiff instead of DAPS at high measurement noiseDDiff · FFHQ phase retrieval, sigma=0.3LPIPS: LPIPS divided by 3 at sigma=0.3Improved
use DDiff instead of DAPS at very low noiseDDiff · FFHQ, sigma<0.05PSNRMixed
DDiff vs DAPS across tasks (Gaussian/motion deblurring, ImageNet phase retrieval)DDiff · FFHQ and ImageNetPSNR: Gaussian deblur FFHQ 28.87 vs 29.63Mixed
apply data consistency in pixel space instead of latent space (LatentDDiff) (ablation)LatentDDiff · latent diffusionreconstruction quality and costImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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