LiDAR-RT: Gaussian-based Ray Tracing for Dynamic LiDAR Re-simulation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915071674810368 |
|---|---|
| author | Zhou, Chenxu Fu, Lvchang Peng, Sida Yan, Yunzhi Zhang, Zhanhua Chen, Yong Xia, Jiazhi Zhou, Xiaowei |
| author_facet | Zhou, Chenxu Fu, Lvchang Peng, Sida Yan, Yunzhi Zhang, Zhanhua Chen, Yong Xia, Jiazhi Zhou, Xiaowei |
| contents | This paper targets the challenge of real-time LiDAR re-simulation in dynamic driving scenarios. Recent approaches utilize neural radiance fields combined with the physical modeling of LiDAR sensors to achieve high-fidelity re-simulation results. Unfortunately, these methods face limitations due to high computational demands in large-scale scenes and cannot perform real-time LiDAR rendering. To overcome these constraints, we propose LiDAR-RT, a novel framework that supports real-time, physically accurate LiDAR re-simulation for driving scenes. Our primary contribution is the development of an efficient and effective rendering pipeline, which integrates Gaussian primitives and hardware-accelerated ray tracing technology. Specifically, we model the physical properties of LiDAR sensors using Gaussian primitives with learnable parameters and incorporate scene graphs to handle scene dynamics. Building upon this scene representation, our framework first constructs a bounding volume hierarchy (BVH), then casts rays for each pixel and generates novel LiDAR views through a differentiable rendering algorithm. Importantly, our framework supports realistic rendering with flexible scene editing operations and various sensor configurations. Extensive experiments across multiple public benchmarks demonstrate that our method outperforms state-of-the-art methods in terms of rendering quality and efficiency. Our project page is at https://zju3dv.github.io/lidar-rt. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_15199 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LiDAR-RT: Gaussian-based Ray Tracing for Dynamic LiDAR Re-simulation Zhou, Chenxu Fu, Lvchang Peng, Sida Yan, Yunzhi Zhang, Zhanhua Chen, Yong Xia, Jiazhi Zhou, Xiaowei Computer Vision and Pattern Recognition Machine Learning Robotics This paper targets the challenge of real-time LiDAR re-simulation in dynamic driving scenarios. Recent approaches utilize neural radiance fields combined with the physical modeling of LiDAR sensors to achieve high-fidelity re-simulation results. Unfortunately, these methods face limitations due to high computational demands in large-scale scenes and cannot perform real-time LiDAR rendering. To overcome these constraints, we propose LiDAR-RT, a novel framework that supports real-time, physically accurate LiDAR re-simulation for driving scenes. Our primary contribution is the development of an efficient and effective rendering pipeline, which integrates Gaussian primitives and hardware-accelerated ray tracing technology. Specifically, we model the physical properties of LiDAR sensors using Gaussian primitives with learnable parameters and incorporate scene graphs to handle scene dynamics. Building upon this scene representation, our framework first constructs a bounding volume hierarchy (BVH), then casts rays for each pixel and generates novel LiDAR views through a differentiable rendering algorithm. Importantly, our framework supports realistic rendering with flexible scene editing operations and various sensor configurations. Extensive experiments across multiple public benchmarks demonstrate that our method outperforms state-of-the-art methods in terms of rendering quality and efficiency. Our project page is at https://zju3dv.github.io/lidar-rt. |
| title | LiDAR-RT: Gaussian-based Ray Tracing for Dynamic LiDAR Re-simulation |
| topic | Computer Vision and Pattern Recognition Machine Learning Robotics |
| url | https://arxiv.org/abs/2412.15199 |