notesum.ai

Published at December 10

PVP: Polar Representation Boost for 3D Semantic Occupancy Prediction

cs.CV

Released Date: December 10, 2024

Authors: Yujing Xue¹, Jiaxiang Liu², Jiawei Du¹, Joey Tianyi Zhou³

Aff.: ¹A*STAR, NUS; ²Zhejiang University; ³A*STAR

Arxiv: http://arxiv.org/pdf/2412.07616v1

Refer to caption

Method	Input	IoU	mIoU	$\blacksquare$ barrier	$\blacksquare$ bicycle	$\blacksquare$ bus	$\blacksquare$ car	$\blacksquare$ const. veh.	$\blacksquare$ motorcycle	$\blacksquare$ pedestrian	$\blacksquare$ traffic cone	$\blacksquare$ trailer	$\blacksquare$ truck	$\blacksquare$ drive. suf.	$\blacksquare$ other flat	$\blacksquare$ sidewalk	$\blacksquare$ terrain	$\blacksquare$ manmade	$\blacksquare$ vegetation
MonoScene [39]	C	18.4	6.9	7.1	3.9	9.3	7.2	5.6	3.0	5.9	4.4	4.9	4.2	14.9	6.3	7.9	7.4	10.0	7.6
TPVFormer [14]	C	15.3	7.8	9.3	4.1	11.3	10.1	5.2	4.3	5.9	5.3	6.8	6.5	13.6	9.0	8.3	8.0	9.2	8.2
3DSketch [40]	C&D	25.6	10.7	12.0	5.1	10.7	12.4	6.5	4.0	5.0	6.3	8.0	7.2	21.8	14.8	13.0	11.8	12.0	21.2
AICNet [33]	C&D	23.8	10.6	11.5	4.0	11.8	12.3	5.1	3.8	6.2	6.0	8.2	7.5	24.1	13.0	12.8	11.5	11.6	20.2
LMSCNet [31]	L	27.3	11.5	12.4	4.2	12.8	12.1	6.2	4.7	6.2	6.3	8.8	7.2	24.2	12.3	16.6	14.1	13.9	22.2
JS3C-Net [32]	L	30.2	12.5	14.2	3.4	13.6	12.0	7.2	4.3	7.3	6.8	9.2	9.1	27.9	15.3	14.9	16.2	14.0	24.9
C-CONet [16]	C	20.1	12.8	13.2	8.1	15.4	17.2	6.3	11.2	10.0	8.3	4.7	12.1	31.4	18.8	18.7	16.3	4.8	8.2
L-CONet [16]	L	30.9	15.8	17.5	5.2	13.3	18.1	7.8	5.4	9.6	5.6	13.2	13.6	34.9	21.5	22.4	21.7	19.2	23.5
M-CONet [16]	C&L	29.5	20.1	23.3	13.3	21.2	24.3	15.3	15.9	18.0	13.3	15.3	20.7	33.2	21.0	22.5	21.5	19.6	23.2
PointOcc [1]	L	34.1	23.9	24.9	19.0	20.9	25.7	13.4	25.6	30.6	17.9	16.7	21.2	36.5	25.6	25.7	24.9	24.8	29.0
PVP (Ours)	L	37.0	25.8	29.9	16.5	23.6	30.4	12.5	23.5	32.5	17.0	20.0	23.9	41.7	26.8	28.4	26.7	28.2	30.5
PVP (Ours)	C&L	36.3	28.0	32.2	24.5	26.7	31.8	16.4	29.9	34.9	21.9	21.5	26.5	40.3	27.5	28.6	26.9	28.5	30.4