4D-ROLLS：基于LiDAR监督的4D雷达占用学习
4D-ROLLS: 4D Radar Occupancy Learning via LiDAR Supervision
AI总结：
针对现有占用估计方法在恶劣环境下表现不佳的问题，提出以LiDAR为监督的4D雷达弱监督占用估计方法4D-ROLLS，性能优异、鲁棒性强，可迁移至下游任务且推理速度快。
摘要：
对3D场景的全面理解对自动驾驶汽车（AVs）至关重要，在各类感知任务中，占用估计通过提供可行驶空间与占用空间的通用表示，发挥着核心作用。然而，现有大多数占用估计方法依赖LiDAR或摄像头，这类设备在烟雾、雨、雪、雾等退化环境中表现不佳。本文提出4D-ROLLS，这是首个以LiDAR点云作为监督信号的4D雷达弱监督占用估计方法。具体而言，我们提出一种生成伪LiDAR标签的方法，包含占用查询和LiDAR高度图，作为多阶段监督来训练4D雷达占用估计模型。随后将该模型与LiDAR生成的占用图对齐，微调其占用估计的精度。大量对比实验验证了4D-ROLLS的优异性能，定性证明了其在退化环境中的鲁棒性以及跨数据集训练的有效性。该模型还可无缝迁移至下游任务BEV分割和点云占用预测，凸显了其更广泛的应用潜力。凭借轻量化网络，4D-ROLLS模型在4060 GPU上可实现约30 Hz的快速推理速度。4D-ROLLS的代码将发布于https://github.com/CLASS-Lab/4D-ROLLS。
英文摘要：
A comprehensive understanding of 3D scenes is essential for autonomous vehicles (AVs), and among various perception tasks, occupancy estimation plays a central role by providing a general representation of drivable and occupied space. However, most existing occupancy estimation methods rely on LiDAR or cameras, which perform poorly in degraded environments such as smoke, rain, snow, and fog. In this paper, we propose 4D-ROLLS, the first weakly supervised occupancy estimation method for 4D radar using the LiDAR point cloud as the supervisory signal. Specifically, we introduce a method for generating pseudo-LiDAR labels, including occupancy queries and LiDAR height maps, as multi-stage supervision to train the 4D radar occupancy estimation model. Then the model is aligned with the occupancy map produced by LiDAR, fine-tuning its accuracy in occupancy estimation. Extensive comparative experiments validate the exceptional performance of 4D-ROLLS. Its robustness in degraded environments and effectiveness in cross-dataset training are qualitatively demonstrated. The model is also seamlessly transferred to downstream tasks BEV segmentation and point cloud occupancy prediction, highlighting its potential for broader applications. The lightweight network enables 4D-ROLLS model to achieve fast inference speeds at about 30 Hz on a 4060 GPU. The code of 4D-ROLLS will be made available at https://github.com/CLASS-Lab/4D-ROLLS.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
