notesum.ai

Published at December 5

Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction

cs.CV

cs.AI

cs.LG

Released Date: December 5, 2024

Authors: Yuanhui Huang¹, Amonnut Thammatadatrakoon¹, Wenzhao Zheng¹, Yunpeng Zhang², Dalong Du², Jiwen Lu²

Aff.: ¹Tsinghua University, China; ²PhiGent Robotics

Arxiv: http://arxiv.org/pdf/2412.04384v1

[Uncaptioned image]

Method	Input	IoU	mIoU	$\blacksquare$ car	$\blacksquare$ bicycle	$\blacksquare$ motorcycle	$\blacksquare$ truck	$\blacksquare$ other-veh.	$\blacksquare$ person	$\blacksquare$ road	$\blacksquare$ parking	$\blacksquare$ sidewalk	$\blacksquare$ other-grnd	$\blacksquare$ building	$\blacksquare$ fence	$\blacksquare$ vegetation	$\blacksquare$ terrain	$\blacksquare$ pole	$\blacksquare$ traf.-sign	$\blacksquare$ other-struct.	$\blacksquare$ other-object
LMSCNet [34]	L	47.53	13.65	20.91	0	0	0.26	0	0	62.95	13.51	33.51	0.2	43.67	0.33	40.01	26.80	0	0	3.63	0
SSCNet [36]	L	53.58	16.95	31.95	0	0.17	10.29	0.58	0.07	65.7	17.33	41.24	3.22	44.41	6.77	43.72	28.87	0.78	0.75	8.60	0.67
MonoScene [3]	C	37.87	12.31	19.34	0.43	0.58	8.02	2.03	0.86	48.35	11.38	28.13	3.22	32.89	3.53	26.15	16.75	6.92	5.67	4.20	3.09
Voxformer [22]	C	38.76	11.91	17.84	1.16	0.89	4.56	2.06	1.63	47.01	9.67	27.21	2.89	31.18	4.97	28.99	14.69	6.51	6.92	3.79	2.43
TPVFormer [13]	C	40.22	13.64	21.56	1.09	1.37	8.06	2.57	2.38	52.99	11.99	31.07	3.78	34.83	4.80	30.08	17.51	7.46	5.86	5.48	2.70
OccFormer [51]	C	40.27	13.81	22.58	0.66	0.26	9.89	3.82	2.77	54.30	13.44	31.53	3.55	36.42	4.80	31.00	19.51	7.77	8.51	6.95	4.60
GaussianFormer [15]	C	35.38	12.92	18.93	1.02	4.62	18.07	7.59	3.35	45.47	10.89	25.03	5.32	28.44	5.68	29.54	8.62	2.99	2.32	9.51	5.14
Ours	C	38.37	13.90	21.08	2.55	4.21	12.41	5.73	1.59	54.12	11.04	32.31	3.34	32.01	4.98	28.94	17.33	3.57	5.48	5.88	3.54