HOG-Layout: Hierarchical 3D Scene Generation, Optimization and Editing via Vision-Language Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908957629480960 |
|---|---|
| author | Jiang, Haiyan Zhang, Deyu Weng, Dongdong Song, Weitao Duh, Henry Been-Lirn |
| author_facet | Jiang, Haiyan Zhang, Deyu Weng, Dongdong Song, Weitao Duh, Henry Been-Lirn |
| contents | 3D layout generation and editing play a crucial role in Embodied AI and immersive VR interaction. However, manual creation requires tedious labor, while data-driven generation often lacks diversity. The emergence of large models introduces new possibilities for 3D scene synthesis. We present HOG-Layout that enables text-driven hierarchical scene generation, optimization and real-time scene editing with large language models (LLMs) and vision-language models (VLMs). HOG-Layout improves scene semantic consistency and plausibility through retrieval-augmented generation (RAG) technology, incorporates an optimization module to enhance physical consistency, and adopts a hierarchical representation to enhance inference and optimization, achieving real-time editing. Experimental results demonstrate that HOG-Layout produces more reasonable environments compared with existing baselines, while supporting fast and intuitive scene editing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_10772 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HOG-Layout: Hierarchical 3D Scene Generation, Optimization and Editing via Vision-Language Models Jiang, Haiyan Zhang, Deyu Weng, Dongdong Song, Weitao Duh, Henry Been-Lirn Computer Vision and Pattern Recognition 3D layout generation and editing play a crucial role in Embodied AI and immersive VR interaction. However, manual creation requires tedious labor, while data-driven generation often lacks diversity. The emergence of large models introduces new possibilities for 3D scene synthesis. We present HOG-Layout that enables text-driven hierarchical scene generation, optimization and real-time scene editing with large language models (LLMs) and vision-language models (VLMs). HOG-Layout improves scene semantic consistency and plausibility through retrieval-augmented generation (RAG) technology, incorporates an optimization module to enhance physical consistency, and adopts a hierarchical representation to enhance inference and optimization, achieving real-time editing. Experimental results demonstrate that HOG-Layout produces more reasonable environments compared with existing baselines, while supporting fast and intuitive scene editing. |
| title | HOG-Layout: Hierarchical 3D Scene Generation, Optimization and Editing via Vision-Language Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.10772 |