AI Paper Atlas

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

I-DRUID: Layout to image generation via instance-disentangled representation and unpaired data

Fengxiang Yang, Tianyi Zheng, Bangjie Yin, Shice Liu, Jinwei Chen, Peng-Tao Jiang, Bo Li

ICLR 2026 · Image generation › Text-to-image diffusion · approach: Layout-to-image control

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 IDM with instance disentanglement constraint (ablation)SD3 L2I baseline · COCO-MIGAvg ISR: 56.82 -> 57.64Improved
add IDM with instance disentanglement constraint (ablation)SD3 L2I baseline · LayoutSAM-evalSpatial: 86.96 -> 88.53Improved
add IDM with instance disentanglement constraint (ablation)SD3 L2I baseline · LayoutSAM-evalShape: 72.44 -> 75.62Improved
add PPO-based RL on unpaired prompts to IDM model (ablation)I-DRUID SD3 · COCO-MIGAvg ISR: 57.64 -> 62.75Improved
add PPO-based RL on unpaired prompts to IDM model (ablation)I-DRUID SD3 · LayoutSAM-evalShape: 75.62 -> 77.20Improved
add IDM to PPO-based RL (ablation)RL-PPO · COCO-MIGAvg ISR: 60.23 -> 62.75Improved
add PPO RL without IDM to baseline (ablation)SD3 L2I baseline · COCO-MIGAvg ISR: 56.82 -> 60.23Improved
use SFT on paired COCO-MIG data instead of unpaired RL (ablation)IDM model · COCO-MIGAvg ISR: 66.92 vs 62.75Mixed
use SFT on paired COCO-MIG data instead of unpaired RL (ablation)IDM model · LayoutSAM-evalTexture: 74.33 vs 78.35Hurt
replace PPO with GRPO (ablation)IDM+RL · COCO-MIGAvg ISR: 61.64 vs 62.75No clear effect
replace PPO with GRPO (ablation)IDM+RL · training speedseconds per iteration: 15s/iter -> more than 60s/iterHurt
lower lambda_dis to 0.5 with lambda_rl 1 (ablation)I-DRUID · COCO-MIGAvg ISR: performance degradation than baselineHurt

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