CVNov 17, 2017

VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection

arXiv:1711.06396v14492 citations
Originality Highly original
AI Analysis

This addresses the need for accurate 3D object detection in applications like autonomous navigation, offering a novel method that improves over existing approaches.

The paper tackles the problem of 3D object detection in sparse LiDAR point clouds by proposing VoxelNet, an end-to-end deep network that eliminates manual feature engineering and unifies feature extraction and bounding box prediction. It achieves state-of-the-art results on the KITTI car detection benchmark and shows promising performance for pedestrians and cyclists.

Accurate detection of objects in 3D point clouds is a central problem in many applications, such as autonomous navigation, housekeeping robots, and augmented/virtual reality. To interface a highly sparse LiDAR point cloud with a region proposal network (RPN), most existing efforts have focused on hand-crafted feature representations, for example, a bird's eye view projection. In this work, we remove the need of manual feature engineering for 3D point clouds and propose VoxelNet, a generic 3D detection network that unifies feature extraction and bounding box prediction into a single stage, end-to-end trainable deep network. Specifically, VoxelNet divides a point cloud into equally spaced 3D voxels and transforms a group of points within each voxel into a unified feature representation through the newly introduced voxel feature encoding (VFE) layer. In this way, the point cloud is encoded as a descriptive volumetric representation, which is then connected to a RPN to generate detections. Experiments on the KITTI car detection benchmark show that VoxelNet outperforms the state-of-the-art LiDAR based 3D detection methods by a large margin. Furthermore, our network learns an effective discriminative representation of objects with various geometries, leading to encouraging results in 3D detection of pedestrians and cyclists, based on only LiDAR.

Code Implementations44 repos

Data from Papers with Code (CC-BY-SA-4.0)

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes