LayoutAgent: A Vision-Language Agent Guided Compositional Diffusion for Spatial Layout Planning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911179202363392 |
|---|---|
| author | Fan, Zezhong Li, Xiaohan Ma, Luyi Zhao, Kai Peng, Liang Biswas, Topojoy Korpeoglu, Evren Nag, Kaushiki Achan, Kannan |
| author_facet | Fan, Zezhong Li, Xiaohan Ma, Luyi Zhao, Kai Peng, Liang Biswas, Topojoy Korpeoglu, Evren Nag, Kaushiki Achan, Kannan |
| contents | Designing realistic multi-object scenes requires not only generating images, but also planning spatial layouts that respect semantic relations and physical plausibility. On one hand, while recent advances in diffusion models have enabled high-quality image generation, they lack explicit spatial reasoning, leading to unrealistic object layouts. On the other hand, traditional spatial planning methods in robotics emphasize geometric and relational consistency, but they struggle to capture semantic richness in visual scenes. To bridge this gap, in this paper, we propose LayoutAgent, an agentic framework that unifies vision-language reasoning with compositional diffusion for layout generation. Given multiple input images with target objects in them, our method first employs visual-language model to preprocess the inputs through segmentation, object size estimation, scene graph construction, and prompt rewriting. Then we leverage compositional diffusion-a method traditionally used in robotics-to synthesize bounding boxes that respect object relations encoded in the scene graph for spatial layouts. In the end, a foreground-conditioned image generator composes the complete scene by rendering the objects into the planned layout guided by designed prompts. Experiments demonstrate that LayoutAgent outperforms other state-of-the-art layout generation models in layout coherence, spatial realism and aesthetic alignment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_22720 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LayoutAgent: A Vision-Language Agent Guided Compositional Diffusion for Spatial Layout Planning Fan, Zezhong Li, Xiaohan Ma, Luyi Zhao, Kai Peng, Liang Biswas, Topojoy Korpeoglu, Evren Nag, Kaushiki Achan, Kannan Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Designing realistic multi-object scenes requires not only generating images, but also planning spatial layouts that respect semantic relations and physical plausibility. On one hand, while recent advances in diffusion models have enabled high-quality image generation, they lack explicit spatial reasoning, leading to unrealistic object layouts. On the other hand, traditional spatial planning methods in robotics emphasize geometric and relational consistency, but they struggle to capture semantic richness in visual scenes. To bridge this gap, in this paper, we propose LayoutAgent, an agentic framework that unifies vision-language reasoning with compositional diffusion for layout generation. Given multiple input images with target objects in them, our method first employs visual-language model to preprocess the inputs through segmentation, object size estimation, scene graph construction, and prompt rewriting. Then we leverage compositional diffusion-a method traditionally used in robotics-to synthesize bounding boxes that respect object relations encoded in the scene graph for spatial layouts. In the end, a foreground-conditioned image generator composes the complete scene by rendering the objects into the planned layout guided by designed prompts. Experiments demonstrate that LayoutAgent outperforms other state-of-the-art layout generation models in layout coherence, spatial realism and aesthetic alignment. |
| title | LayoutAgent: A Vision-Language Agent Guided Compositional Diffusion for Spatial Layout Planning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2509.22720 |