preprintJul 12, 2024GOLD OA

2D Gaussian Splatting for Geometrically Accurate Radiance Fields

ShanghaiTech University · University of Tübingen

Indexed inarxivcrossref

Abstract

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…

Citation impact

430
total citations
FWCI
237.92
Percentile
100%
References
39
Citations per year

Authors

5

Topics & keywords

Keywords
  • Radiance
  • Computer science
  • Gaussian
  • Computer graphics (images)
  • Artificial intelligence
  • Computer vision
  • Remote sensing
  • Geology
No related works found for this paper.