From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network

TL;DR

This paper introduces Part-A^2 net, a novel 3D object detection framework from LiDAR point clouds that leverages part-aware and part-aggregation modules to improve detection accuracy and achieve state-of-the-art results.

Contribution

The paper proposes a new framework that fully utilizes part supervisions and intra-object part locations for improved 3D detection from point clouds.

Findings

Outperforms existing 3D detection methods on KITTI dataset.

Achieves state-of-the-art performance using only LiDAR data.

Demonstrates effectiveness of part-aware and aggregation modules.

Abstract

3D object detection from LiDAR point cloud is a challenging problem in 3D scene understanding and has many practical applications. In this paper, we extend our preliminary work PointRCNN to a novel and strong point-cloud-based 3D object detection framework, the part-aware and aggregation neural network (Part-$A^2$ net). The whole framework consists of the part-aware stage and the part-aggregation stage. Firstly, the part-aware stage for the first time fully utilizes free-of-charge part supervisions derived from 3D ground-truth boxes to simultaneously predict high quality 3D proposals and accurate intra-object part locations. The predicted intra-object part locations within the same proposal are grouped by our new-designed RoI-aware point cloud pooling module, which results in an effective representation to encode the geometry-specific features of each 3D proposal. Then the part-aggregation stage learns to re-score the box and refine the box location by exploring the spatial relationship of the pooled intra-object part locations. Extensive experiments are conducted to demonstrate the performance improvements from each component of our proposed framework. Our Part-$A^2$ net outperforms all existing 3D detection methods and achieves new state-of-the-art on KITTI 3D object detection dataset by utilizing only the LiDAR point cloud data. Code is available at https://github.com/sshaoshuai/PointCloudDet3D.