2D Gaussian Splatting for Geometrically Accurate Radiance Fields

doi:10.1145/3641519.3657428

	2D Gaussian Splatting for Geometrically Accurate Radiance Fields
	Huang, Binbin1 ; Yu, Zehao 2; Chen, Anpei 2; Geiger, Andreas 2; Gao, Shenghua1
	2024-07-13
会议录名称	PROCEEDINGS - SIGGRAPH 2024 CONFERENCE PAPERS
DOI	10.1145/3641519.3657428
摘要	3D Gaussian Splatting (3DGS) has recently revolutionized radiance field reconstruction, achieving high quality novel view synthesis and fast rendering speed. However, 3DGS fails to accurately represent surfaces due to the multi-view inconsistent nature of 3D Gaussians. We present 2D Gaussian Splatting (2DGS), a novel approach to model and reconstruct geometrically accurate radiance fields from multi-view images. Our key idea is to collapse the 3D volume into a set of 2D oriented planar Gaussian disks. Unlike 3D Gaussians, 2D Gaussians provide view-consistent geometry while modeling surfaces intrinsically. To accurately recover thin surfaces and achieve stable optimization, we introduce a perspective-accurate 2D splatting process utilizing ray-splat intersection and rasterization. Additionally, we incorporate depth distortion and normal consistency terms to further enhance the quality of the reconstructions. We demonstrate that our differentiable renderer allows for noise-free and detailed geometry reconstruction while maintaining competitive appearance quality, fast training speed, and real-time rendering. © 2024 Owner/Author.
会议录编者/会议主办者	ACM SIGGRAPH
会议名称	SIGGRAPH 2024 Conference Papers
会议地点	Denver, CO, United states
会议日期	July 28, 2024 - August 1, 2024
URL	查看原文
收录类别	EI
语种	英语
出版者	Association for Computing Machinery, Inc
EI入藏号	20243116789678
原始文献类型	Conference article (CA)
引用统计
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/411254
专题	信息科学与技术学院_博士生信息科学与技术学院_PI研究组_高盛华组
作者单位	1.ShanghaiTech University, Shanghai, China 2.University of Tübingen, Tübingen AI Center, Tübingen, Germany
第一作者单位	上海科技大学
第一作者的第一单位	上海科技大学
推荐引用方式 GB/T 7714	Huang, Binbin,Yu, Zehao,Chen, Anpei,et al. 2D Gaussian Splatting for Geometrically Accurate Radiance Fields[C]//ACM SIGGRAPH:Association for Computing Machinery, Inc,2024.