SynCity: Training-Free Generation of 3D Worlds
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909545896345600 |
|---|---|
| author | Engstler, Paul Shtedritski, Aleksandar Laina, Iro Rupprecht, Christian Vedaldi, Andrea |
| author_facet | Engstler, Paul Shtedritski, Aleksandar Laina, Iro Rupprecht, Christian Vedaldi, Andrea |
| contents | We address the challenge of generating 3D worlds from textual descriptions. We propose SynCity, a training- and optimization-free approach, which leverages the geometric precision of pre-trained 3D generative models and the artistic versatility of 2D image generators to create large, high-quality 3D spaces. While most 3D generative models are object-centric and cannot generate large-scale worlds, we show how 3D and 2D generators can be combined to generate ever-expanding scenes. Through a tile-based approach, we allow fine-grained control over the layout and the appearance of scenes. The world is generated tile-by-tile, and each new tile is generated within its world-context and then fused with the scene. SynCity generates compelling and immersive scenes that are rich in detail and diversity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_16420 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SynCity: Training-Free Generation of 3D Worlds Engstler, Paul Shtedritski, Aleksandar Laina, Iro Rupprecht, Christian Vedaldi, Andrea Computer Vision and Pattern Recognition We address the challenge of generating 3D worlds from textual descriptions. We propose SynCity, a training- and optimization-free approach, which leverages the geometric precision of pre-trained 3D generative models and the artistic versatility of 2D image generators to create large, high-quality 3D spaces. While most 3D generative models are object-centric and cannot generate large-scale worlds, we show how 3D and 2D generators can be combined to generate ever-expanding scenes. Through a tile-based approach, we allow fine-grained control over the layout and the appearance of scenes. The world is generated tile-by-tile, and each new tile is generated within its world-context and then fused with the scene. SynCity generates compelling and immersive scenes that are rich in detail and diversity. |
| title | SynCity: Training-Free Generation of 3D Worlds |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.16420 |