AI Paper Atlas

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

Lay-Your-Scene: Natural Scene Layout Generation with Diffusion Transformers

Divyansh Srivastava, Xiang Zhang, He Wen, Chenru Wen, Zhuowen Tu

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 6 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
use LayouSyn diffusion layout generator instead of LayoutGPT (GPT-4o-mini)LayoutGPT · COCO-GR validationL-FID: 6.72 -> 3.07Improved
add GRIT pretraining (ablation)LayouSyn · COCO-GR validationL-FID: 3.07 -> 3.31Hurt
add GRIT pretraining (ablation)LayouSyn · NSR-1K spatial reasoningaccuracy: 87.49 -> 92.58Improved
add GRIT pretraining (ablation)LayouSyn · NSR-1K spatial reasoningGLIP accuracy: 54.91 -> 58.94Improved
use LayouSyn instead of LayoutGPT with fixed GPT-4o-mini description setLayoutGPT · COCO-GR L-FIDL-FID: 6.72 -> 3.32Improved
generate description set with Llama-3.1-8B instead of GPT-3.5 (ablation)LayouSyn · COCO-GR L-FIDL-FID: 3.49 -> 2.74Improved
increase DDIM sampling steps from 10 to 100 (ablation)LayouSyn · COCO-GR L-FIDL-FID: 3.47 -> 2.74Improved
add cross-attention between prompt and description tokens (ablation)LDiT block · COCO-GR L-FIDL-FID: 2.82 -> 2.81No clear effect
add modulation of description tokens on top of cross-attention (ablation)LDiT block · COCO-GR L-FIDL-FID: 2.81 -> 2.74Improved
increase noise schedule scale s to 2.0 with CFG 2.0 (ablation)LayouSyn · COCO-GR L-FIDL-FIDImproved
initialize with DDIM inversion of LLM layout plus description set (vs description set only)LayouSyn · NSR-1K spatial reasoning (Llama-3.1-8B)accuracy: 89.75 -> 90.46Improved
use LayouSyn description set + inversion on GPT-4o-mini layoutsLayoutGPT (GPT-4o-mini) · NSR-1K spatial reasoningaccuracy: 92.01 -> 92.08No clear effect

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