AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Triadic Dynamics Aware Diffusion Posterior Sampling for Inverse Problems: Optimizing Guidance and Stochasticity Schedules

Junseo Bang, Dong Ju Mun, Hoigi Seo, Seongmin Hong, Se Young Chun

ICML 2026 · Image generation › Fast diffusion sampling · approach: Diffusion posterior sampling · 0 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
schedule DC, CFG and stochasticity jointly instead of keeping all fixed (ablation)TriPS (SD3.5-M) · FFHQ SR x8LPIPS: 0.155 -> 0.101Improved
schedule only DC guidance (others fixed) (ablation)TriPS · FFHQ SR x8LPIPS: 0.155 -> 0.125Improved
schedule only CFG (others fixed) (ablation)TriPS · FFHQ SR x8PSNR: 29.04 -> 29.05No clear effect
schedule only stochasticity (others fixed) (ablation)TriPS · FFHQ SR x8LPIPS: 0.155 -> 0.133Improved
add GRPO schedule optimization on top of template searchTriPST · FFHQ SR x8 (flow matching)FID: 26.66 -> 22.18Improved
add GRPO schedule optimization on top of template searchTriPST · FFHQ SR x8 (flow matching)PSNR: 29.03 -> 28.55Hurt
use distortion-weighted GRPO reward (w_dist 0.9) (ablation)TriPS_G · FFHQ Gaussian deblurringPSNR: 30.33 -> 30.62Improved
use perception-weighted GRPO reward (w_perc 0.7) (ablation)TriPS_G · FFHQ Gaussian deblurringLPIPS: 0.070 -> 0.067Improved
transfer schedule optimized on SR x8 to Gaussian deblurringTriPS_G · FFHQ 100 samplesPSNR: 27.74 -> 28.90Improved
transfer schedule optimized on SR x8 to SR x12TriPS_G · FFHQ 100 samplesLPIPS: 0.148 -> 0.099Improved
apply TriPS schedules to SD1.5 diffusion backbone vs TRegTriPS · FFHQ SR x8 (50 NFE)PSNR: 26.34 -> 28.02Improved
raise CFG scale early in sampling (ablation)posterior sampling · DIV2K SR x8residual norm decayHurt

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