将3D高斯点云快速转为激光雷达可用网格，支持超高速仿真。
FGGS-LiDAR: Ultra-Fast, GPU-Accelerated Simulation from General 3DGS Models to LiDAR
- 从高斯参数直接生成封闭网格，无需额外训练或修改架构。
- 激光雷达仿真速度超500帧/秒，支持4096环境并行模拟。
- 适用于机器人与自动驾驶，显著降低仿真延迟，优于Isaac Sim。
尽管3D高斯点云（3DGS）已成为逼真渲染的有力表示，其庞大的资产生态仍难以用于高性能激光雷达仿真，而该技术对机器人与自动驾驶至关重要。本文提出FGGS-LiDAR，一种几何优先的即插即用框架，可直接从高斯参数转换预训练3DGS资产为封闭网格，无需激光雷达特定监督或结构改动，通过体素化与截断有符号距离场（TSDF）提取实现。结合GPU加速的射线投射模块，可在超过500 FPS下模拟激光雷达回波，并支持最多4096个环境的批量并行仿真。在大规模并行设置中，相比Isaac Sim，FGGS-LiDAR实现数量级更低的仿真延迟。我们在室内外场景中验证了其高保真度激光雷达仿真效果。此外，在基于COLMAP姿态的室内基准上，对比现有3DGS到网格基线，报告更低的激光雷达仿真误差。代码已开源：https://github.com/discoverse-dev/FGGS-LiDAR。
原文摘要 · Abstract (English)
While 3D Gaussian Splatting (3DGS) has emerged as a strong representation for photorealistic rendering, its vast ecosystem of assets remains difficult to use for high-performance LiDAR simulation, a critical tool for robotics and autonomous driving. We present \textbf{FGGS-LiDAR}, a geometry-first framework that bridges this gap in a plug-and-play manner. Our method converts pretrained 3DGS assets into watertight meshes directly from Gaussian parameters, without requiring LiDAR-specific supervision or architectural alterations, via volumetric discretization and Truncated Signed Distance Field (TSDF) extraction. We pair this with a GPU-accelerated ray-casting module that simulates LiDAR returns at over 500 FPS and supports batched multi-environment simulation with up to 4096 environments. In large-scale parallel settings, FGGS-LiDAR achieves an order-of-magnitude lower LiDAR simulation latency than Isaac Sim. We validate FGGS-LiDAR on both indoor and outdoor scenes, demonstrating high LiDAR-simulation fidelity. Furthermore, on COLMAP-posed indoor benchmarks, we compare against existing 3DGS-to-mesh baselines and report lower LiDAR-simulation error. Code is at https://github.com/discoverse-dev/FGGS-LiDAR.
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。