论文标题
激光蒸馏：桥接梁诱导的域间隙以进行3D对象检测
LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection
论文作者
论文摘要
在本文中，我们提出了激光蒸馏以弥合由不同的激光束引起的3D对象检测的域间隙。在许多现实世界中，大规模生产的机器人和车辆使用的激光点通常比大型公共数据集的光束少。此外，随着LIDARS升级到具有不同光束量的其他产品模型，使用先前版本的高分辨率传感器捕获的标记数据变得具有挑战性。尽管域自适应3D检测最近取得了进展，但大多数方法都难以消除光束诱导的域间隙。我们发现，在训练过程中，将源域的点云密度与目标域的点密度保持一致。受到这一发现的启发，我们提出了一个渐进式框架来减轻梁引起的域移位。在每次迭代中，我们首先通过下采样高光束点云来产生低光束伪激光雷达。然后，使用教师学生框架将丰富的信息从数据中提取更多的横梁。 Waymo，Nuscenes和Kitti数据集的大量实验具有三个不同的基于激光雷达的探测器，这证明了我们的LIDAR蒸馏的有效性。值得注意的是，我们的方法不会增加任何推理的额外计算成本。
In this paper, we propose the LiDAR Distillation to bridge the domain gap induced by different LiDAR beams for 3D object detection. In many real-world applications, the LiDAR points used by mass-produced robots and vehicles usually have fewer beams than that in large-scale public datasets. Moreover, as the LiDARs are upgraded to other product models with different beam amount, it becomes challenging to utilize the labeled data captured by previous versions' high-resolution sensors. Despite the recent progress on domain adaptive 3D detection, most methods struggle to eliminate the beam-induced domain gap. We find that it is essential to align the point cloud density of the source domain with that of the target domain during the training process. Inspired by this discovery, we propose a progressive framework to mitigate the beam-induced domain shift. In each iteration, we first generate low-beam pseudo LiDAR by downsampling the high-beam point clouds. Then the teacher-student framework is employed to distill rich information from the data with more beams. Extensive experiments on Waymo, nuScenes and KITTI datasets with three different LiDAR-based detectors demonstrate the effectiveness of our LiDAR Distillation. Notably, our approach does not increase any additional computation cost for inference.
