3D Object Detection On Kitti Pedestrians

Results

Performance results of various models on this benchmark

Model Name	AP	Paper Title	Repository
HotSpotNet	44.81%	Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots	-
SVGA-Net	47.71%	SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds	-
IPOD	44.68%	IPOD: Intensive Point-based Object Detector for Point Cloud	-
Frustum PointNets	42.15%	Frustum PointNets for 3D Object Detection from RGB-D Data	-
3D-FCT	58.4%	3D-FCT: Simultaneous 3D Object Detection and Tracking Using Feature Correlation	-
STD	44.24%	STD: Sparse-to-Dense 3D Object Detector for Point Cloud	-
M3DeTR	41.02%	M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers	-
AVOD + Feature Pyramid	42.81%	Joint 3D Proposal Generation and Object Detection from View Aggregation	-
VoxelNet	33.69%	VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection	-
F-ConvNet	43.38%	Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection	-
Frustrum-PointPillars	42.89 %	Frustum-PointPillars: A Multi-Stage Approach for 3D Object Detection using RGB Camera and LiDAR
PointPillars	41.92%	PointPillars: Fast Encoders for Object Detection from Point Clouds	-

0 of 12 row(s) selected.