Multi-View 3D Object Detection Network for Autonomous Driving
Abstract
This paper aims at high-accuracy 3D object detection in autonomous driving scenario. We propose Multi-View 3D networks (MV3D), a sensory-fusion framework that takes both LIDAR point cloud and RGB images as input and predicts oriented 3D bounding boxes. We encode the sparse 3D point cloud with a compact multi-view representation. The network is composed of two subnetworks: one for 3D object proposal generation and another for multi-view feature fusion. The proposal network generates 3D candidate boxes efficiently from the bird's eye view representation of 3D point cloud. We design a deep fusion scheme to combine region-wise features from multiple views and enable interactions between intermediate layers of different paths. Experiments on the challenging KITTI benchmark show that our approach outperforms the state-of-the-art by around 25% and 30% AP on the tasks of 3D localization and 3D detection. In addition, for 2D detection, our approach obtains 10.3% higher AP than the state-of-the-art on the hard data among the LIDAR-based methods.
Cite
@article{arxiv.1611.07759,
title = {Multi-View 3D Object Detection Network for Autonomous Driving},
author = {Xiaozhi Chen and Huimin Ma and Ji Wan and Bo Li and Tian Xia},
journal= {arXiv preprint arXiv:1611.07759},
year = {2017}
}
Comments
To appear in IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017