Multi-Level Neural Scene Graphs for Dynamic Urban Environments
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910392472567808 |
|---|---|
| author | Fischer, Tobias Porzi, Lorenzo Bulò, Samuel Rota Pollefeys, Marc Kontschieder, Peter |
| author_facet | Fischer, Tobias Porzi, Lorenzo Bulò, Samuel Rota Pollefeys, Marc Kontschieder, Peter |
| contents | We estimate the radiance field of large-scale dynamic areas from multiple vehicle captures under varying environmental conditions. Previous works in this domain are either restricted to static environments, do not scale to more than a single short video, or struggle to separately represent dynamic object instances. To this end, we present a novel, decomposable radiance field approach for dynamic urban environments. We propose a multi-level neural scene graph representation that scales to thousands of images from dozens of sequences with hundreds of fast-moving objects. To enable efficient training and rendering of our representation, we develop a fast composite ray sampling and rendering scheme. To test our approach in urban driving scenarios, we introduce a new, novel view synthesis benchmark. We show that our approach outperforms prior art by a significant margin on both established and our proposed benchmark while being faster in training and rendering. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_00168 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-Level Neural Scene Graphs for Dynamic Urban Environments Fischer, Tobias Porzi, Lorenzo Bulò, Samuel Rota Pollefeys, Marc Kontschieder, Peter Computer Vision and Pattern Recognition We estimate the radiance field of large-scale dynamic areas from multiple vehicle captures under varying environmental conditions. Previous works in this domain are either restricted to static environments, do not scale to more than a single short video, or struggle to separately represent dynamic object instances. To this end, we present a novel, decomposable radiance field approach for dynamic urban environments. We propose a multi-level neural scene graph representation that scales to thousands of images from dozens of sequences with hundreds of fast-moving objects. To enable efficient training and rendering of our representation, we develop a fast composite ray sampling and rendering scheme. To test our approach in urban driving scenarios, we introduce a new, novel view synthesis benchmark. We show that our approach outperforms prior art by a significant margin on both established and our proposed benchmark while being faster in training and rendering. |
| title | Multi-Level Neural Scene Graphs for Dynamic Urban Environments |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.00168 |