AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

InstanceControl: Controllable Complex Image Generation without Instance Labeling

XIAOYU LIU, Huan Wang, FAN LI, Zhixing Wang, Jiaqi Xu, Ming LIU, Wangmeng Zuo

ECCV 2026 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 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 VLM-derived instance correspondences (no manual labels)FLUX ControlNet · MIG-Eval CannyMIoU: 0.6526 -> 0.8250Improved
add VLM correspondences with predicted masks, no refinement (ablation)FLUX ControlNet · MIG-Evalaverage accuracy: 77.78% -> 87.97%Improved
add mask refinement module (MRM) (ablation)InstanceControl · MIG-Evalaverage accuracy: 87.97% -> 90.10%Improved
add interactive mask correctionInstanceControl · MIG-Evalaverage accuracy: 90.10% -> 93.19%Improved
add Shared SEG Token (ablation)InstanceControl · MIG-Eval CannyMIoU: 0.8214 -> 0.8250Improved
use MRM refined mask instead of raw predicted mask (ablation)InstanceControl · MIG-Eval CannyFID: 10.9284 -> 10.0264Improved
use MRM instead of score-based fusion of masks (ablation)InstanceControl · MIG-Eval CannyMIoU: 0.8210 -> 0.8250Improved
use InstanceControl instead of unified models (Qwen-Image ControlNet, Nano Banana)generation · MIG-Eval 300 imagesMIoU: 0.8307 -> 0.8834Improved
use InstanceControl vs FLUX ControlNet under depthFLUX ControlNet · MIG-Eval DepthImageReward: 0.3216 -> 0.2961Hurt

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