SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929612866453504 |
|---|---|
| author | Bokhovkin, Alexey Meng, Quan Tulsiani, Shubham Dai, Angela |
| author_facet | Bokhovkin, Alexey Meng, Quan Tulsiani, Shubham Dai, Angela |
| contents | We present SceneFactor, a diffusion-based approach for large-scale 3D scene generation that enables controllable generation and effortless editing. SceneFactor enables text-guided 3D scene synthesis through our factored diffusion formulation, leveraging latent semantic and geometric manifolds for generation of arbitrary-sized 3D scenes. While text input enables easy, controllable generation, text guidance remains imprecise for intuitive, localized editing and manipulation of the generated 3D scenes. Our factored semantic diffusion generates a proxy semantic space composed of semantic 3D boxes that enables controllable editing of generated scenes by adding, removing, changing the size of the semantic 3D proxy boxes that guides high-fidelity, consistent 3D geometric editing. Extensive experiments demonstrate that our approach enables high-fidelity 3D scene synthesis with effective controllable editing through our factored diffusion approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_01801 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation Bokhovkin, Alexey Meng, Quan Tulsiani, Shubham Dai, Angela Computer Vision and Pattern Recognition We present SceneFactor, a diffusion-based approach for large-scale 3D scene generation that enables controllable generation and effortless editing. SceneFactor enables text-guided 3D scene synthesis through our factored diffusion formulation, leveraging latent semantic and geometric manifolds for generation of arbitrary-sized 3D scenes. While text input enables easy, controllable generation, text guidance remains imprecise for intuitive, localized editing and manipulation of the generated 3D scenes. Our factored semantic diffusion generates a proxy semantic space composed of semantic 3D boxes that enables controllable editing of generated scenes by adding, removing, changing the size of the semantic 3D proxy boxes that guides high-fidelity, consistent 3D geometric editing. Extensive experiments demonstrate that our approach enables high-fidelity 3D scene synthesis with effective controllable editing through our factored diffusion approach. |
| title | SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.01801 |