3D scene generation from scene graphs and self-attention
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913327201910784 |
|---|---|
| author | Bonazzi, Pietro Wang, Mengqi Arroyo, Diego Martin Manhardt, Fabian Messikomer, Nico Tombari, Federico Scaramuzza, Davide |
| author_facet | Bonazzi, Pietro Wang, Mengqi Arroyo, Diego Martin Manhardt, Fabian Messikomer, Nico Tombari, Federico Scaramuzza, Davide |
| contents | Synthesizing realistic and diverse indoor 3D scene layouts in a controllable fashion opens up applications in simulated navigation and virtual reality. As concise and robust representations of a scene, scene graphs have proven to be well-suited as the semantic control on the generated layout. We present a variant of the conditional variational autoencoder (cVAE) model to synthesize 3D scenes from scene graphs and floor plans. We exploit the properties of self-attention layers to capture high-level relationships between objects in a scene, and use these as the building blocks of our model. Our model, leverages graph transformers to estimate the size, dimension and orientation of the objects in a room while satisfying relationships in the given scene graph. Our experiments shows self-attention layers leads to sparser (7.9x compared to Graphto3D) and more diverse scenes (16%). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_01887 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | 3D scene generation from scene graphs and self-attention Bonazzi, Pietro Wang, Mengqi Arroyo, Diego Martin Manhardt, Fabian Messikomer, Nico Tombari, Federico Scaramuzza, Davide Computer Vision and Pattern Recognition Synthesizing realistic and diverse indoor 3D scene layouts in a controllable fashion opens up applications in simulated navigation and virtual reality. As concise and robust representations of a scene, scene graphs have proven to be well-suited as the semantic control on the generated layout. We present a variant of the conditional variational autoencoder (cVAE) model to synthesize 3D scenes from scene graphs and floor plans. We exploit the properties of self-attention layers to capture high-level relationships between objects in a scene, and use these as the building blocks of our model. Our model, leverages graph transformers to estimate the size, dimension and orientation of the objects in a room while satisfying relationships in the given scene graph. Our experiments shows self-attention layers leads to sparser (7.9x compared to Graphto3D) and more diverse scenes (16%). |
| title | 3D scene generation from scene graphs and self-attention |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.01887 |