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

Table 5

Results on the KITTI test 3D 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	71.09	62.35	55.12	N/A	N/A	N/A	N/A	N/A	N/A
Cont-Fuse [37]	16.7	N/A	82.54	66.22	64.04	N/A	N/A	N/A	N/A	N/A	N/A
Roarnet [38]	10	N/A	83.71	73.04	59.16	N/A	N/A	N/A	N/A	N/A	N/A
AVOD-FPN [39]	10	55.62	81.94	71.88	66.38	50.80	42.81	40.88	64.00	52.18	46.61
F-PointNet [40]	5.9	57.35	81.20	70.39	62.19	51.21	44.89	40.23	71.96	56.77	50.39
VoxelNet	4.4	49.05	77.47	65.11	57.73	39.48	33.69	31.50	61.22	48.36	44.37
SECOND	20	56.69	83.13	73.66	66.20	51.07	42.56	37.29	70.51	53.85	46.90
PointPillars	62	59.20	79.05	74.99	68.30	52.08	43.53	41.49	75.78	59.07	52.92
Ours	34	63.08	87.48	76.22	73.55	54.78	49.45	43.07	81.69	63.58	60.55