AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Noise-Adaptive Diffusion Sampling for Inverse Problems Without Task-Specific Tuning

Yingzhi Xia, Setthakorn Tanomkiattikun, Liangli Zhen, ZAIWANG GU

ICLR 2026 · Image generation › Fast diffusion sampling · approach: Diffusion posterior sampling · 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 NA-NHMC instead of best baseline on nonlinear tasks (FFHQ, sigma 0.05)NA-NHMC · FFHQ phase retrievalPSNR: 18.52 -> 19.30Improved
use NA-NHMC instead of DPSNA-NHMC · FFHQ HDR reconstructionLPIPS: 0.168 vs 0.217Hurt
use NA-NHMC instead of SITCOM on linear sigma 0.05NA-NHMC · FFHQ SR x4PSNR: 27.35 vs 27.29No clear effect
use NA-NHMC at high noise sigma_y=0.20 (vs MAP-like DAPS)NA-NHMC · FFHQ Gaussian deblurringPSNR: 8.12 -> 25.57Improved
use NA-NHMC under impulse noise without retuningNA-NHMC · FFHQ nonlinear deblurringPSNR: 23.79 -> 24.16Improved
use NA-NHMC under speckle noiseNA-NHMC · FFHQ nonlinear deblurringPSNR: 26.49 -> 27.97Improved
increase leapfrog steps L from 10 to 25 (ablation)NA-NHMC · FFHQ SR x4PSNR: 26.86 -> 27.36Improved
increase initial step size from 0.02 to 0.10 (ablation)NA-NHMC · FFHQ SR x4PSNR: 27.12 -> 27.31Improved
vary step size decay gamma from 0.91 to 0.99 (ablation)NA-NHMC · FFHQ SR x4PSNR: 27.29 -> 27.30No clear effect
use NA-NHMC instead of SITCOM at SR x16, sigma 0.05NA-NHMC · FFHQ SR x16SSIM: 0.574 vs 0.531Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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