2DGS: 2D Gaussian Splatting
for Geometrically Accurate Radiance Fields

  • 1ShanghaiTech University    
  • 2University of Tübingen    
  • 3Tübingen AI Center    

2DGS adopts (a) 2D oriented disks as surface elements and allows (b) high-quality rendering with gaussian splatting.
Use the slider as the "splatter"


3D Gaussian Splatting (3DGS) has recently revolutionized radiance field reconstruction, achieving high quality novel view synthesis and fast rendering speed without baking. 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.


Geometry Reconstruction

3DGS (upper) V.S. 2DGS (below)

Our textured mesh

Radiance Field Rendering


If you want to cite our work, please use:

    title={2D Gaussian Splatting for Geometrically Accurate Radiance Fields},
    author={Huang, Binbin and Yu, Zehao and Chen, Anpei and Geiger, Andreas and Gao, Shenghua},


The website template was borrowed from Michaël Gharbi and MipNeRF360.