AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Geometry-Correct Diffusion Posterior Sampling with Denoiser-Pullback Curvature Guidance and Manifold-Aligned Damping

Seunghyeok Shin, Minwoo Kim, Dabin Kim, Hongki Lim

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
add variance-preserving Langevin transition instead of ODE-style update (ablation)CLAMP · FFHQ/ImageNet inverse problemsreconstruction qualityImproved
add prior-aligned rank-one damping (ablation)CLAMP · FFHQ/ImageNet inverse problemsreconstruction qualityImproved
keep the denoiser pullback J_F^T in the curvature model (ablation)CLAMP · FFHQ/ImageNet inverse problemsaccuracyImproved
use full curvature including forward J_F instead of one-sided (ablation)CLAMP · FFHQ/ImageNet inverse problemsaccuracy vs runtimeNo clear effect
use GMRES instead of CG for the nonsymmetric system (ablation)CLAMP · FFHQ/ImageNet inverse problemsstabilityImproved
CLAMP vs SITCOM on pixel FFHQ motion deblurringCLAMP · FFHQ motion deblurringrun-time: 4.14x speedupImproved
CLAMP vs Latent DAPS in latent spaceLatent CLAMP · latent-space inverse problemsrun-time: 2.4x fasterImproved
CLAMP vs ReSample in latent spaceLatent CLAMP · latent-space inverse problemsrun-time: 9x fasterImproved
CLAMP vs best baseline on MRI x4CLAMP · SKM-TEA MRI x4PSNR: 32.21 -> 34.05Improved
CLAMP vs best baseline on MRI x8CLAMP · SKM-TEA MRI x8PSNR: 30.29 -> 32.27Improved
CLAMP vs DAPS on ImageNet phase retrievalCLAMP · ImageNet phase retrievalPSNR: 22.354 -> 19.680Hurt
CLAMP vs SITCOM on FFHQ Gaussian deblurringCLAMP · FFHQ Gaussian deblurringPSNR: 29.359 -> 29.010Hurt

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