AI Paper Atlas

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

CoMPaSS: Enhancing Spatial Understanding in Text-to-Image Diffusion Models

Gaoyang Zhang, Bingtao Fu, Qingnan Fan, Qi Zhang, Runxing Liu, Hong Gu, Huaqi Zhang, Xinguo Liu

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 10 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 CoMPaSS (SCOP data + TENOR)FLUX.1 · VISOR uncondaccuracy: 37.96 -> 75.17Improved
add CoMPaSSFLUX.1 · T2I-CompBench Spatialscore: 0.18 -> 0.30Improved
add CoMPaSSFLUX.1 · GenEval Positionscore: 0.26 -> 0.60Improved
add CoMPaSSSD1.5 · GenEval Positionscore: 0.04 -> 0.54Improved
add CoMPaSSFLUX.1 · DPG-Bench overallscore: 80.63 -> 84.42Improved
add CoMPaSSSD2.1 · FIDFID: 21.65 -> 16.96Improved
add CoMPaSSSD1.5 · FIDFID: 12.82 -> 10.89Hurt
add SCOP dataset fine-tuning (ablation)SD1.5 · GenEval Positionscore: 0.04 -> 0.39Improved
add SCOP dataset fine-tuning (ablation)FLUX.1 · GenEval Positionscore: 0.26 -> 0.56Improved
add TENOR on top of SCOP (ablation)SD1.5 · GenEval Positionscore: 0.39 -> 0.54Improved
add TENOR on top of SCOP (ablation)FLUX.1 · GenEval Positionscore: 0.56 -> 0.60Improved
add TENOR on top of SCOP (ablation)FLUX.1 · T2I-CompBench Spatialscore: 0.29 -> 0.30Improved

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