notesum.ai

Published at May 11

Effective Rank Analysis and Regularization for Enhanced 3D Gaussian Splatting

NeurIPS

Released Date: May 11, 2024

Authors: Junha Hyung¹, Susung Hong², Sungwon Hwang¹, Jaeseong Lee¹, Jaegul Choo¹, Jin-Hwa Kim³

Aff.: ¹KAIST; ²Korea University; ³NAVER AI Lab, SNU AIIS

Arxiv: https://openreview.net/pdf/fc3623f0ad337417db48cc4a09f4de75bc2958b8.pdf

Refer to caption

Method	24	37	40	55	63	65	69	83	97	105	106	110	114	118	122	Mean	Std.	PSNR
3DGS	2.14	1.53	2.08	1.68	3.49	2.21	1.43	2.07	2.22	1.75	1.79	2.55	1.53	1.52	1.50	1.96	0.52	32.82
3DGS+e	0.86	0.77	0.88	0.52	1.29	1.44	0.96	1.30	2.09	0.72	0.87	1.40	0.88	0.94	0.66	1.04	0.39	33.09
SuGaR	1.47	1.33	1.13	0.61	2.25	1.71	1.15	1.63	1.62	1.07	0.79	2.45	0.98	0.88	0.79	1.33	0.52	31.59
SuGaR+e	0.86	0.78	0.89	0.53	1.28	1.45	0.87	1.31	1.60	0.72	0.86	1.45	0.87	0.94	0.66	1.00	0.33	31.76
2DGS	0.48	0.91	0.39	0.39	1.01	0.83	0.81	1.36	1.27	0.76	0.70	1.40	0.40	0.76	0.52	0.80	0.33	32.43
2DGS+e	0.46	0.86	0.39	0.40	0.96	0.84	0.81	1.29	1.19	0.72	0.70	1.32	0.40	0.75	0.50	0.77	0.30	32.57
GOF	0.50	0.82	0.37	0.37	1.12	0.78	0.73	1.18	1.29	0.71	0.77	0.90	0.44	0.69	0.49	0.74	0.28	32.88
GOF+e	0.45	0.66	0.32	0.42	0.97	0.78	0.64	1.13	1.22	0.64	0.62	0.70	0.40	0.53	0.48	0.66	0.26	33.01