We present DrivingGaussian, an efficient and effective framework for surrounding dynamic autonomous driving scenes. For complex scenes with moving objects, we first sequentially and progressively model the static background of the entire scene with incremental static 3D Gaussians. We then leverage a composite dynamic Gaussian graph to handle multiple moving objects, individually reconstructing each object and restoring their accurate positions and occlusion relationships within the scene. We further use a LiDAR prior for Gaussian Splatting to reconstruct scenes with greater details and maintain panoramic consistency. DrivingGaussian outperforms existing methods in driving scene reconstruction and enables photorealistic surround-view synthesis with high-fidelity and multi-camera consistency. Our project page is at: https://github.com/VDIGPKU/DrivingGaussian.

翻译：我们提出了DrivingGaussian，一个高效且有效的框架，用于处理环绕动态自动驾驶场景。针对包含移动物体的复杂场景，我们首先通过增量式静态三维高斯函数逐步顺序建模整个场景的静态背景。随后，我们利用复合动态高斯图处理多个移动物体，分别重建每个物体并恢复其在场景中的精确位置与遮挡关系。为进一步提升细节重建与全景一致性，我们采用激光雷达先验辅助高斯泼溅。DrivingGaussian在驾驶场景重建中优于现有方法，能够生成具有高保真度与多相机一致性的逼真环绕视图合成。我们的项目主页位于：https://github.com/VDIGPKU/DrivingGaussian。