3D Object Detection On Kitti Cyclists Easy

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名	AP	Paper Title	Repository
Frustum PointNets	71.96%	Frustum PointNets for 3D Object Detection from RGB-D Data
PointRCNN	73.93%	PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud
VoxelNet	61.22%	VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
AVOD + Feature Pyramid	64.0%	Joint 3D Proposal Generation and Object Detection from View Aggregation
M3DeTR	83.83%	M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers
STD	78.89%	STD: Sparse-to-Dense 3D Object Detector for Point Cloud	-
F-ConvNet	79.58%	Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection
3D-FCT	89.15%	3D-FCT: Simultaneous 3D Object Detection and Tracking Using Feature Correlation	-
IPOD	71.40%	IPOD: Intensive Point-based Object Detector for Point Cloud	-
SVGA-Net	79.22%	SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds	-
PointPillars	75.78%	PointPillars: Fast Encoders for Object Detection from Point Clouds
PV-RCNN	78.60%	PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

0 of 12 row(s) selected.