Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting
This work addresses the slow training and rendering speeds in dynamic urban scene modeling for autonomous driving applications, offering a significant improvement in efficiency and performance.
The paper tackles the problem of modeling dynamic urban streets for autonomous driving scenes by introducing Street Gaussians, an explicit scene representation that achieves 135 FPS rendering at high resolution with half an hour of training and outperforms state-of-the-art methods on benchmarks like KITTI and Waymo Open.
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.