3D Object Detection Algorithm Based on the Reconstruction of Sparse Point Clouds in the Viewing Frustum

Table 1

3D object detection AP values of various algorithms in the 3D view with the KITTI test set.

Method	Cars			Pedestrians			Cyclists
	Easy	Moderate	Hard	Easy	Moderate	Hard	Easy	Moderate	Hard
MV3D	71.29	62.68	56.56
VoxelNet	81.97	65.46	62.85	39.48	33.69	31.50	61.22	48.36	44.37
Pointpillars	79.05	74.99	68.30	52.08	43.53	41.47	75.78	59.07	52.92
F-PointNet	80.62	64.70	56.07	50.88	41.55	38.04	69.36	53.50	52.88
Ours	83.81	71.80	64.17	65.57	57.94	50.77	78.75	58.92	55.70