Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916360098938880 |
|---|---|
| author | Yan, Yunzhi Lin, Haotong Zhou, Chenxu Wang, Weijie Sun, Haiyang Zhan, Kun Lang, Xianpeng Zhou, Xiaowei Peng, Sida |
| author_facet | Yan, Yunzhi Lin, Haotong Zhou, Chenxu Wang, Weijie Sun, Haiyang Zhan, Kun Lang, Xianpeng Zhou, Xiaowei Peng, Sida |
| contents | This paper aims to tackle the problem of modeling dynamic urban streets for autonomous driving scenes. Recent methods extend NeRF by incorporating tracked vehicle poses to animate vehicles, enabling photo-realistic view synthesis of dynamic urban street scenes. However, significant limitations are their slow training and rendering speed. We introduce Street Gaussians, a new explicit scene representation that tackles these limitations. Specifically, the dynamic urban scene is represented as a set of point clouds equipped with semantic logits and 3D Gaussians, each associated with either a foreground vehicle or the background. To model the dynamics of foreground object vehicles, each object point cloud is optimized with optimizable tracked poses, along with a 4D spherical harmonics model for the dynamic appearance. The explicit representation allows easy composition of object vehicles and background, which in turn allows for scene editing operations and rendering at 135 FPS (1066 $\times$ 1600 resolution) within half an hour of training. The proposed method is evaluated on multiple challenging benchmarks, including KITTI and Waymo Open datasets. Experiments show that the proposed method consistently outperforms state-of-the-art methods across all datasets. The code will be released to ensure reproducibility. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_01339 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting Yan, Yunzhi Lin, Haotong Zhou, Chenxu Wang, Weijie Sun, Haiyang Zhan, Kun Lang, Xianpeng Zhou, Xiaowei Peng, Sida Computer Vision and Pattern Recognition Graphics This paper aims to tackle the problem of modeling dynamic urban streets for autonomous driving scenes. Recent methods extend NeRF by incorporating tracked vehicle poses to animate vehicles, enabling photo-realistic view synthesis of dynamic urban street scenes. However, significant limitations are their slow training and rendering speed. We introduce Street Gaussians, a new explicit scene representation that tackles these limitations. Specifically, the dynamic urban scene is represented as a set of point clouds equipped with semantic logits and 3D Gaussians, each associated with either a foreground vehicle or the background. To model the dynamics of foreground object vehicles, each object point cloud is optimized with optimizable tracked poses, along with a 4D spherical harmonics model for the dynamic appearance. The explicit representation allows easy composition of object vehicles and background, which in turn allows for scene editing operations and rendering at 135 FPS (1066 $\times$ 1600 resolution) within half an hour of training. The proposed method is evaluated on multiple challenging benchmarks, including KITTI and Waymo Open datasets. Experiments show that the proposed method consistently outperforms state-of-the-art methods across all datasets. The code will be released to ensure reproducibility. |
| title | Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2401.01339 |