3D Object Detection On Kitti Cars Hard Val

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	AP	Paper Title	Repository
PVCNN	63.81	Point-Voxel CNN for Efficient 3D Deep Learning
F-PointNet [Qi:2018fd]	62.56	Frustum PointNets for 3D Object Detection from RGB-D Data
MV3D	56.56	Multi-View 3D Object Detection Network for Autonomous Driving
PV-RCNN++	82.69	PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection
SVGA-Net	79.15	SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds	-
Voxel R-CNN	78.93	Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection
SA-SSD+EBM	82.23	Accurate 3D Object Detection using Energy-Based Models
PGD	16.9	Probabilistic and Geometric Depth: Detecting Objects in Perspective
M3DeTR	82.85	M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers
PC-RGNN	80.45	PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detection	-

0 of 10 row(s) selected.