用神经辐射场生成汽车雷达点云，实现多传感器联合仿真。
NeuRadar: Neural Radiance Fields for Automotive Radar Point Clouds
- 基于NeRF构建雷达点云生成模型，融合相机与激光雷达数据。
- 在两个汽车数据集上实现逼真重建，验证了模型有效性。
- 支持确定性与概率性表示，适配雷达的随机特性，适合自动驾驶研发。
雷达因在恶劣天气和不同光照条件下表现稳定，是自动驾驶系统的重要传感器。近年来，神经辐射场（NeRF）在新视角合成方面备受关注，有望提升自动驾驶系统的测试与验证效率，但其在雷达点云领域的应用尚未被探索。本文提出NeuRadar，一种基于NeRF的模型，可联合生成雷达点云、相机图像和激光雷达点云。我们采用基于集合的对象检测方法（如DETR），并提出一种基于NeRF几何结构的编码器方案，以提升模型泛化能力。为准确建模雷达行为，我们设计了确定性和概率性两种点云表示方式，后者可捕捉雷达的随机特性。在两个汽车数据集上实现了逼真重建结果，建立了基于NeRF的雷达点云模拟基准。此外，我们公开了ZOD数据集中的序列和驾驶场景雷达数据，并发布NeuRadar源代码，以推动该领域研究发展。
原文摘要 · Abstract (English)
Radar is an important sensor for autonomous driving (AD) systems due to its robustness to adverse weather and different lighting conditions. Novel view synthesis using neural radiance fields (NeRFs) has recently received considerable attention in AD due to its potential to enable efficient testing and validation but remains unexplored for radar point clouds. In this paper, we present NeuRadar, a NeRF-based model that jointly generates radar point clouds, camera images, and lidar point clouds. We explore set-based object detection methods such as DETR, and propose an encoder-based solution grounded in the NeRF geometry for improved generalizability. We propose both a deterministic and a probabilistic point cloud representation to accurately model the radar behavior, with the latter being able to capture radar's stochastic behavior. We achieve realistic reconstruction results for two automotive datasets, establishing a baseline for NeRF-based radar point cloud simulation models. In addition, we release radar data for ZOD's Sequences and Drives to enable further research in this field. To encourage further development of radar NeRFs, we release the source code for NeuRadar.
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。