B
Bo Li
Researcher at Baidu
Publications - 33
Citations - 6135
Bo Li is an academic researcher from Baidu. The author has contributed to research in topics: Point cloud & RANSAC. The author has an hindex of 16, co-authored 33 publications receiving 3682 citations. Previous affiliations of Bo Li include ETH Zurich & Peking University.
Papers
More filters
Proceedings ArticleDOI
Multi-view 3D Object Detection Network for Autonomous Driving
TL;DR: This paper proposes 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 and designs a deep fusion scheme to combine region-wise features from multiple views and enable interactions between intermediate layers of different paths.
Journal ArticleDOI
SECOND: Sparsely Embedded Convolutional Detection
Yan Yan,Yuxing Mao,Bo Li +2 more
TL;DR: An improved sparse convolution method for Voxel-based 3D convolutional networks is investigated, which significantly increases the speed of both training and inference and introduces a new form of angle loss regression to improve the orientation estimation performance.
Proceedings ArticleDOI
3D fully convolutional network for vehicle detection in point cloud
TL;DR: The fully convolutional network based detection techniques to 3D and apply to point cloud data is extended and verified on the task of vehicle detection from lidar point cloud for autonomous driving.
Proceedings ArticleDOI
Vehicle Detection from 3D Lidar Using Fully Convolutional Network
Bo Li,Zhang Tianlei,Xia Tian +2 more
TL;DR: In this article, a 2D point map and a single 2D end-to-end fully convolutional network are used to predict the objectness confidence and the bounding boxes simultaneously.
Posted Content
Vehicle Detection from 3D Lidar Using Fully Convolutional Network
Bo Li,Zhang Tianlei,Xia Tian +2 more
TL;DR: In this paper, a 2D point map and a single 2D end-to-end fully convolutional network are used to predict the objectness confidence and the bounding boxes simultaneously.