论文标题
范围条件扩张的卷积量表不变3D对象检测
Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detection
论文作者
论文摘要
本文提出了一个新颖的3D对象检测框架，该框架直接在其本机表示上处理LiDAR数据：范围图像。从范围图像的紧凑性中受益，2D卷积可以有效地处理场景的密集雷达数据。为了克服尺度灵敏度，提出了一种新型的范围条件扩张（RCD）层，以动态调整连续扩张速率，这是测得的范围的函数。此外，局部软范围门控结合了3D盒子式阶段，可改善咬合区域的鲁棒性，并产生总体上更准确的边界框预测。在公共大规模Waymo打开数据集中，我们的方法为基于范围的3D检测设置了一个新的基线，比在远距离检测的所有范围内都超过了所有范围的基于范围的多视图和基于体素的方法。
This paper presents a novel 3D object detection framework that processes LiDAR data directly on its native representation: range images. Benefiting from the compactness of range images, 2D convolutions can efficiently process dense LiDAR data of a scene. To overcome scale sensitivity in this perspective view, a novel range-conditioned dilation (RCD) layer is proposed to dynamically adjust a continuous dilation rate as a function of the measured range. Furthermore, localized soft range gating combined with a 3D box-refinement stage improves robustness in occluded areas, and produces overall more accurate bounding box predictions. On the public large-scale Waymo Open Dataset, our method sets a new baseline for range-based 3D detection, outperforming multiview and voxel-based methods over all ranges with unparalleled performance at long range detection.
