Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection

5 Mar 2019Zhixin WangKui Jia

In this work, we propose a novel method termed \emph{Frustum ConvNet (F-ConvNet)} for amodal 3D object detection from point clouds. Given 2D region proposals in an RGB image, our method first generates a sequence of frustums for each region proposal, and uses the obtained frustums to group local points... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
3D Object Detection KITTI Cars Easy F-ConvNet AP 85.88% # 7
3D Object Detection KITTI Cars Hard F-ConvNet AP 68.08% # 7
3D Object Detection KITTI Cars Moderate F-ConvNet AP 76.51% # 6
3D Object Detection KITTI Cyclists Easy F-ConvNet AP 79.58% # 1
3D Object Detection KITTI Cyclists Hard F-ConvNets AP 57.03% # 3
3D Object Detection KITTI Cyclists Moderate F-ConvNet AP 64.68% # 2
3D Object Detection KITTI Pedestrians Easy F-ConvNet AP 52.37% # 4
3D Object Detection KITTI Pedestrians Hard F-ConvNet AP 41.49% # 4
3D Object Detection KITTI Pedestrians Moderate F-ConvNet AP 43.38% # 5

Methods used in the Paper