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.

该论文研究了自动驾驶场景下高精度的 3D 物体检测问题。其提出了 Multi-View 3D networks（MV3D）框架，该框架采用多传感器融合技术，将 LIDAR 点云和 RGB 图像作为输入，并预测有方向的 3D 界限框。实验表明，该方法在 3D 定位和 3D 检测任务方面的表现优于现有技术约 25％和 30％，在 2D 检测中也表现出显著的技术优势。