用摄像头生成占据栅格，实现低成本高精度自动驾驶场景重建
OG-Gaussian: Occupancy Based Street Gaussians for Autonomous Driving
- 用相机图像生成占据栅格替代激光雷达点云
- 重建质量达35.13 PSNR，渲染速度143 FPS
- 无需人工标注，适合仿真环境构建者
精确的3D场景重建可生成逼真的自动驾驶仿真环境。随着3D高斯溅射（3DGS）的发展，已有研究将其应用于复杂动态驾驶场景重建，但通常依赖昂贵的激光雷达和预标注动态物体数据集。为此，我们提出OG-Gaussian，用环绕相机图像生成的占据栅格（OGs）替代激光雷达点云，通过占据预测网络（ONet）获取。该方法利用占据栅格中的语义信息分离动态车辆与静态街景，将栅格转换为两组初始点云，分别用于重建静态与动态物体。此外，通过学习方法估计动态物体轨迹与位姿，避免复杂人工标注。在Waymo Open数据集上的实验表明，OG-Gaussian在重建质量与渲染速度方面达到当前最优水平，平均PSNR为35.13，渲染速度达143 FPS，同时显著降低计算成本与经济开销。
原文摘要 · Abstract (English)
Accurate and realistic 3D scene reconstruction enables the lifelike creation of autonomous driving simulation environments. With advancements in 3D Gaussian Splatting (3DGS), previous studies have applied it to reconstruct complex dynamic driving scenes. These methods typically require expensive LiDAR sensors and pre-annotated datasets of dynamic objects. To address these challenges, we propose OG-Gaussian, a novel approach that replaces LiDAR point clouds with Occupancy Grids (OGs) generated from surround-view camera images using Occupancy Prediction Network (ONet). Our method leverages the semantic information in OGs to separate dynamic vehicles from static street background, converting these grids into two distinct sets of initial point clouds for reconstructing both static and dynamic objects. Additionally, we estimate the trajectories and poses of dynamic objects through a learning-based approach, eliminating the need for complex manual annotations. Experiments on Waymo Open dataset demonstrate that OG-Gaussian is on par with the current state-of-the-art in terms of reconstruction quality and rendering speed, achieving an average PSNR of 35.13 and a rendering speed of 143 FPS, while significantly reducing computational costs and economic overhead.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。