Pillar-Based 3D Object Detection from Point Cloud with Multiattention Mechanism

Table 4

Results on the KITTI test BEV detection benchmark.

Model	Speed (Hz)	mAP	Car			Pedestrian			Cyclist
		Mod.	Easy (%)	Mod. (%)	Hard (%)	Easy (%)	Mod. (%)	Hard (%)	Easy (%)	Mod. (%)	Hard (%)
MV3D [36]	2.8	N/A	86.02	76.90	68.49	N/A	N/A	N/A	N/A	N/A	N/A
Cont-Fuse [37]	16.7	N/A	88.81	85.83	77.33	N/A	N/A	N/A	N/A	N/A	N/A
Roarnet [38]	10	N/A	88.20	79.41	70.02	N/A	N/A	N/A	N/A	N/A	N/A
AVOD-FPN [39]	10	64.11	88.53	83.79	77.90	58.75	51.05	47.54	68.09	57.48	50.77
F-PointNet [40]	5.9	65.39	88.70	84.00	75.33	58.09	50.22	47.20	75.38	61.96	54.68
HDNET [41]	20	N/A	89.14	86.57	78.32	N/A	N/A	N/A	N/A	N/A	N/A
PIXOR++ [41]	35	N/A	89.38	83.70	77.97	N/A	N/A	N/A	N/A	N/A	N/A
VoxelNet	4.4	58.25	89.35	79.26	77.39	46.13	40.74	38.11	66.70	54.76	50.55
SECOND	20	60.56	88.07	79.37	77.95	55.10	46.27	44.76	73.67	56.04	48.78
PointPillars	62	66.19	88.35	86.10	79.83	58.66	50.23	47.19	79.14	62.25	56.00
Ours	34	69.96	92.76	88.37	85.31	60.67	54.13	48.22	82.22	67.38	59.86