[论文解读] IPOD: Intensive Point-based Object Detector for Point Cloud

Zetong Yang, Yanan Sun+3 more|arXiv (Cornell University)|Dec 13, 2018

Remote Sensing and LiDAR Applications参考文献 33被引用 132

一句话总结

IPOD 从原始点云的每个点出发产生对象候选，使用基于点的骨干网络在上下文中提取候选特征，并端到端预测3D边界框，在 KITTI 上取得最先进的结果，尤其是在困难情形下。

ABSTRACT

We present a novel 3D object detection framework, named IPOD, based on raw point cloud. It seeds object proposal for each point, which is the basic element. This paradigm provides us with high recall and high fidelity of information, leading to a suitable way to process point cloud data. We design an end-to-end trainable architecture, where features of all points within a proposal are extracted from the backbone network and achieve a proposal feature for final bounding inference. These features with both context information and precise point cloud coordinates yield improved performance. We conduct experiments on KITTI dataset, evaluating our performance in terms of 3D object detection, Bird's Eye View (BEV) detection and 2D object detection. Our method accomplishes new state-of-the-art , showing great advantage on the hard set.

研究动机与目标

• 直接在原始点云上进行3D目标检测的动机，不使用体素化或投影。
• 开发逐点候选生成策略，以保持定位保真度和高召回率。
• 设计端到端结构，在提取候选特征时结合上下文信息与精确的点坐标。
• 通过新颖的标注与对齐方案解决基于点的候选中的冗余和歧义。
• 在 KITTI 的 Car、Pedestrian 和 Cyclist 任务上展示最先进的性能，尤其在遮挡和混乱场景下。

提出的方法

• 在每个点的中心种子化对象候选，使用多尺度、多个角度的平移。
• 使用子采样网络滤除背景点并保持高召回率（KITTI 上为 96.0%）。
• 采用 PointNet++ 骨干从原始点云提取逐点特征。
• 通过将高层上下文特征与规范化的点坐标和 T-Net 中心化残差相结合来生成候选特征。
• 用多任务损失（L_cls、L_loc、L_ang、L_cor、L_corner）预测每个候选的类别、尺寸比、中心残差和方位。
• 使用 PointsIoU 而非普通框 IoU 来对齐候选并分配正/负标签，以更好地反映点级重叠。

实验结果

研究问题

• RQ1 Can a per-point proposal generation paradigm on raw point clouds achieve higher recall and better 3D detection, BEV, and 2D metrics without voxelization or projection?
• RQ2 Does incorporating context features and canonized point coordinates within proposal representations improve localization and classification?
• RQ3 How does PointsIoU-based labeling affect training stability and final detection performance compared to traditional IoU-based labeling?
• RQ4 What is the impact of subsampling, proposal feature design, and backbone choice on KITTI Car, Pedestrian, and Cyclist detection performance?

主要发现

• Achieves state-of-the-art results on KITTI, with notable gains on the hard subset for 2D, BEV, and 3D AP compared to prior methods.
• Outperforms F-PointNet and multi-view methods, especially for pedestrians and crowded scenes.
• Demonstrates high recall (96.0%) without projection-based preprocessing.
• Ablations show that PointsIoU labeling and the combination of high-level context features with canonized coordinates significantly improve AP (Table 3 and Table 5).
• Beats VoxelNet and AVOD baselines in 3D and BEV detections on KITTI val set (Car, Pedestrian, Cyclist) across Easy/Moderate/Hard levels.