AI Paper Atlas

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

Dual Optimal Transport for Multi-Concept Composition: Structural Alignment and Texture Injection in Diffusion Models

Hao Fu, Tianyu Su, Meng Liu, Chenfang Yang, Tian Gan

ICML 2026 · Image generation › Text-to-image diffusion · approach: Multi-concept composition

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 Barycentric Soft-Transport structure sketching on top of layout planning (ablation)OTComp · qualitative (Figure 5)visual alignment of color, shape, poseImproved
add Geometry-Guided Transport texture rendering after structure sketching (ablation)OTComp · qualitative (Figure 5)high-frequency identity detailImproved
use barycentric projection guidance instead of directly minimizing Sinkhorn loss (ablation)Barycentric Soft-Transport · qualitative (Figure 6a)structural stabilityImproved
use OT-based transport instead of rigid Spatial MSE feature matching (ablation)Barycentric Soft-Transport · qualitative (Figure 6b)identity under pose changeImproved
apply structural guidance early t in [5, 20] rather than late t < 10 (ablation)Barycentric Soft-Transport · qualitative (Figure 6c)texture preservationImproved
add Barycentric Soft-Transport to MRSA attention (Ours+MRSA vs SDXL+MRSA) (ablation)OTComp · qualitative (Figure 7)semantic leakageImproved
replace MRSA with concept-wise masked attention CWSA (ablation)OTComp · qualitative (Figure 7)semantic leakage and identityImproved
use OTComp vs training-free and tuned baselines on four-concept compositionOTComp · MagicBench (four concepts)DINO: 0.5175 -> 0.6844Improved

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