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
会议录名称	PROCEEDINGS OF SIGGRAPH 2024 CONFERENCE PAPERS
发表状态	已发表
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. Project page at https://surfsplatting.github.io.
关键词	Novel View Synthesis Radiance Fields Surface Splatting Surface Reconstruction
会议名称	SIGGRAPH Conference on Emerging Technologies
出版地	1601 Broadway, 10th Floor, NEW YORK, NY, UNITED STATES
会议地点	null,Denver,CO
会议日期	JUL 28-AUG 01, 2024
URL	查看原文
收录类别	CPCI-S
语种	英语
资助项目	NSFC["62172279","61932020"] ; ERC[850533] ; DFG EXC["2064/1","390727645"]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods
WOS记录号	WOS:001282218200034
出版者	ASSOC COMPUTING MACHINERY
引用统计	正在获取...
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/372948
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
通讯作者	Huang, Binbin
作者单位	1.ShanghaiTech Univ, Shanghai, Peoples R China 2.Univ Tubingen, Tubingen AI Ctr, Tubingen, Germany
第一作者单位	上海科技大学
通讯作者单位	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]. 1601 Broadway, 10th Floor, NEW YORK, NY, UNITED STATES:ASSOC COMPUTING MACHINERY,2024.