AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

From Open Loop to Closed Loop: A Test-Time Iterative Optimization Framework for Reference-Consistent Image Generation

Baixuan Zhao, Xinyu Zhang, 华渝 郑, Shuaicheng Liu, Xiongkuo Min, Guangtao Zhai, Xiaohong Liu

ECCV 2026 · Image generation › Fast diffusion sampling · approach: Distillation for few-step generation · 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 closed-loop feedback vs best-of-20 open loopPuLID · CelebA300facial similarity: 0.560 -> 0.702Improved
add closed-loop feedback vs best-of-20 open loopPMv2 · Web100facial similarity: 0.598 -> 0.684Improved
add closed-loop feedback vs best-of-20 open loopInstantID · CelebA300facial similarity: 0.817 -> 0.878Improved
add closed-loop feedback vs best-of-20 open loopIPA · Web100facial similarity: 0.684 -> 0.731Improved
add closed-loop feedback vs best-of-15 open loopControlNet · Pose-controlled generationMPJPE: 36.521 -> 26.401Improved
add closed-loop feedback vs best-of-15 open loopControlNet · Depth-controlled generationMAE: 15.797 -> 11.295Improved
add closed-loop feedback vs best-of-15 open loopControlNext · Pose-controlled generationMPJPE: 75.827 -> 65.623Improved
add closed-loop feedback vs best-of-15 open loopControlNext · Depth-controlled generationMAE: 29.598 -> 25.331Improved
add integral term to P controller (ablation)Closed-loop PID · Identity (50 samples)facial similarity: 0.694 -> 0.723Improved
add derivative term to PI controller (ablation)Closed-loop PID · Identity (50 samples)facial similarity: 0.723 -> 0.724No clear effect
add derivative term to P controller (ablation)Closed-loop PID · Identity (50 samples)iterations to 95% gain: 5.58 -> 5.52Improved
add closed-loop feedback with no text prompt (ablation)Base generator · Prompt-level ablation, depthMAE: 22.598 -> 14.553Improved

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