SemLayoutDiff: Semantic Layout Generation with Diffusion Model for Indoor Scene Synthesis
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912573868212224 |
|---|---|
| author | Sun, Xiaohao Goel, Divyam Chang, Angel X. |
| author_facet | Sun, Xiaohao Goel, Divyam Chang, Angel X. |
| contents | We present SemLayoutDiff, a unified model for synthesizing diverse 3D indoor scenes across multiple room types. The model introduces a scene layout representation combining a top-down semantic map and attributes for each object. Unlike prior approaches, which cannot condition on architectural constraints, SemLayoutDiff employs a categorical diffusion model capable of conditioning scene synthesis explicitly on room masks. It first generates a coherent semantic map, followed by a cross-attention-based network to predict furniture placements that respect the synthesized layout. Our method also accounts for architectural elements such as doors and windows, ensuring that generated furniture arrangements remain practical and unobstructed. Experiments on the 3D-FRONT dataset show that SemLayoutDiff produces spatially coherent, realistic, and varied scenes, outperforming previous methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_18597 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SemLayoutDiff: Semantic Layout Generation with Diffusion Model for Indoor Scene Synthesis Sun, Xiaohao Goel, Divyam Chang, Angel X. Graphics Computer Vision and Pattern Recognition We present SemLayoutDiff, a unified model for synthesizing diverse 3D indoor scenes across multiple room types. The model introduces a scene layout representation combining a top-down semantic map and attributes for each object. Unlike prior approaches, which cannot condition on architectural constraints, SemLayoutDiff employs a categorical diffusion model capable of conditioning scene synthesis explicitly on room masks. It first generates a coherent semantic map, followed by a cross-attention-based network to predict furniture placements that respect the synthesized layout. Our method also accounts for architectural elements such as doors and windows, ensuring that generated furniture arrangements remain practical and unobstructed. Experiments on the 3D-FRONT dataset show that SemLayoutDiff produces spatially coherent, realistic, and varied scenes, outperforming previous methods. |
| title | SemLayoutDiff: Semantic Layout Generation with Diffusion Model for Indoor Scene Synthesis |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.18597 |