AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Stochastic Optimal Control Sampling for Diffusion Inverse Problems

Jie Zhang, Youmei Qiu, Hanling Tian, Jingyuan Zhang, Xiang Yin, Xiaolin Huang

ECCV 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
use SOCS-Nonlinear-gamma instead of SOCS-Linear for 4x super-resolution on FFHQ (FID) (ablation)SOCS · FFHQ 4x SRFID: 72.99 -> 76.86Hurt
use nonlinear refinement instead of linear projection on nonlinear deblurring (ablation)SOCS · FFHQ nonlinear deblurPSNR: 21.73 -> 28.29Improved
use nonlinear refinement instead of linear projection on motion deblurring (ablation)SOCS · FFHQ motion deblurPSNR: 26.53 -> 29.74Improved
use finite terminal penalty gamma instead of gamma to infinity on box inpainting (ablation)SOCS-Nonlinear · FFHQ box inpaintingFID: 55.26 -> 43.79Improved
use finite terminal penalty gamma instead of gamma to infinity on random inpainting (ablation)SOCS-Nonlinear · FFHQ random inpaintingFID: 55.42 -> 52.73Improved
use finite terminal penalty gamma on high dynamic range reconstruction (ablation)SOCS-Nonlinear · FFHQ high dynamic rangePSNR: 26.30 -> 24.31Hurt
use finite terminal penalty gamma on phase retrieval (ablation)SOCS-Nonlinear · FFHQ phase retrievalFID: 52.43 -> 44.86Improved
use SOCS-Nonlinear-gamma instead of strongest baseline DAPS on 4x SRSOCS · ImageNet 4x SRFID: 112.60 -> 93.77Improved
apply SOCS on SD3-medium instead of FlowDPS for x12 super-resolutionSD3-medium · FFHQ 768x768 SR x12 (Avgpool)FID: 65.00 -> 53.61Improved
increase gamma towards infinity (ablation)SOCS · multiple tasksperceptual qualityHurt
use very small gamma (~10^3) (ablation)SOCS · super-resolution, phase retrievalquality / consistencyHurt
vary gamma within 10^5 to 10^9 (ablation)SOCS · multiple tasksmetricsNo clear effect

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