· 2024
2D Gaussian Splatting for Geometrically Accurate Radiance Fields
- 474citations
- 2024year
Short summary
2D Gaussian Splatting (2DGS) reconstructs geometrically accurate radiance fields by collapsing 3D Gaussians into view-consistent 2D planar Gaussian disks, overcoming 3DGS's surface representation limitations.
AI-generated from the title and abstract; the full text is not read.
Key points
- 2DGS models radiance fields using view-consistent 2D planar Gaussian disks, unlike the multi-view inconsistent 3D Gaussians.
- A perspective-accurate 2D splatting process with ray-splat intersection and rasterization is used for accurate thin surface reconstruction.
- Depth distortion and normal consistency terms are incorporated to enhance reconstruction quality.
- 2DGS achieves noise-free geometry, competitive appearance, fast training, and real-time rendering.
AI-generated from the title and abstract; the full text is not read.
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 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.
The authors' abstract, as published at the source., 2024 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computer Graphics and Computer-Aided Design
Computer Graphics and Computer-Aided DesignComputer Science