3D Object Detection On Kitti Cyclists Hard

Results

Performance results of various models on this benchmark

Model Name	AP	Paper Title	Repository
F-ConvNets	57.03%	Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection
Frustum PointNets	50.39%	Frustum PointNets for 3D Object Detection from RGB-D Data
IPOD	48.34%	IPOD: Intensive Point-based Object Detector for Point Cloud	-
AVOD + Feature Pyramid	46.61%	Joint 3D Proposal Generation and Object Detection from View Aggregation
M3DeTR	59.03%	M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers
PointPillars	52.92%	PointPillars: Fast Encoders for Object Detection from Point Clouds
PointRCNN	53.59%	PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud
PV-RCNN	57.65%	PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
SA-Det3D	61.33%	SA-Det3D: Self-Attention Based Context-Aware 3D Object Detection
STD	55.77%	STD: Sparse-to-Dense 3D Object Detector for Point Cloud	-
SVGA-Net	57.64%	SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds	-
VoxelNet	44.37%	VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection

0 of 12 row(s) selected.