FGGS-LiDAR: Ultra-Fast, GPU-Accelerated Simulation from General 3DGS Models to LiDAR
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914050487615488 |
|---|---|
| author | Wu, Junzhe Jia, Yufei Yan, Yiyi Chen, Zhixing Tan, Tiao Wang, Zifan Wang, Guangyu |
| author_facet | Wu, Junzhe Jia, Yufei Yan, Yiyi Chen, Zhixing Tan, Tiao Wang, Zifan Wang, Guangyu |
| contents | While 3D Gaussian Splatting (3DGS) has revolutionized photorealistic rendering, its vast ecosystem of assets remains incompatible with high-performance LiDAR simulation, a critical tool for robotics and autonomous driving. We present \textbf{FGGS-LiDAR}, a framework that bridges this gap with a truly plug-and-play approach. Our method converts \textit{any} pretrained 3DGS model into a high-fidelity, watertight mesh without requiring LiDAR-specific supervision or architectural alterations. This conversion is achieved through a general pipeline of volumetric discretization and Truncated Signed Distance Field (TSDF) extraction. We pair this with a highly optimized, GPU-accelerated ray-casting module that simulates LiDAR returns at over 500 FPS. We validate our approach on indoor and outdoor scenes, demonstrating exceptional geometric fidelity; By enabling the direct reuse of 3DGS assets for geometrically accurate depth sensing, our framework extends their utility beyond visualization and unlocks new capabilities for scalable, multimodal simulation. Our open-source implementation is available at https://github.com/TATP-233/FGGS-LiDAR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17390 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FGGS-LiDAR: Ultra-Fast, GPU-Accelerated Simulation from General 3DGS Models to LiDAR Wu, Junzhe Jia, Yufei Yan, Yiyi Chen, Zhixing Tan, Tiao Wang, Zifan Wang, Guangyu Robotics 68T40, 68U05 I.6.8 While 3D Gaussian Splatting (3DGS) has revolutionized photorealistic rendering, its vast ecosystem of assets remains incompatible with high-performance LiDAR simulation, a critical tool for robotics and autonomous driving. We present \textbf{FGGS-LiDAR}, a framework that bridges this gap with a truly plug-and-play approach. Our method converts \textit{any} pretrained 3DGS model into a high-fidelity, watertight mesh without requiring LiDAR-specific supervision or architectural alterations. This conversion is achieved through a general pipeline of volumetric discretization and Truncated Signed Distance Field (TSDF) extraction. We pair this with a highly optimized, GPU-accelerated ray-casting module that simulates LiDAR returns at over 500 FPS. We validate our approach on indoor and outdoor scenes, demonstrating exceptional geometric fidelity; By enabling the direct reuse of 3DGS assets for geometrically accurate depth sensing, our framework extends their utility beyond visualization and unlocks new capabilities for scalable, multimodal simulation. Our open-source implementation is available at https://github.com/TATP-233/FGGS-LiDAR. |
| title | FGGS-LiDAR: Ultra-Fast, GPU-Accelerated Simulation from General 3DGS Models to LiDAR |
| topic | Robotics 68T40, 68U05 I.6.8 |
| url | https://arxiv.org/abs/2509.17390 |