2D Gaussian Splatting for Geometrically Accurate Radiance Fields
By Binbin Huang, Zehao Yu, Anpei Chen, Andreas Geiger, Shenghua Gao. International Conference on Computer Graphics and Interactive Techniques, 2024
1,465 citations recorded by the source corpus.
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.
Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design
View Paper: https://www.semanticscholar.org/paper/9c0d40f01ced7d425cb6145e9f961c6e44a478a8
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computational Mechanics
In Computer Graphics and Computer-Aided Design
Citations in the corpus
- PGSR: Planar-Based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction (2024, positive): “We also compared it with recently emerged reconstruction methods based on 3DGS, such as SuGaR [21], 2DGS [55], and GOF [56].”
- A Survey on 3D Gaussian Splatting (2024, neutral): “In SLAM , [140, 203], where environmental dynamics demand real-time map updates, requires explicit modeling of dynamic adjustments ( e.g ., object motions and interactions), material compliance, etc .”
- Gen3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control (2025, neutral): “Generating novel views from a set of posed images has seen significant progress [25, 35, 50], with numerous extensions towards large scene reconstruction [3, 28, 62, 71], improved rendering quality [2, 21, 58], faster rendering speed [37, 58] and handling dynamic scenes [11, 32].”
- Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes (2024, methodology): “The results of implicit methods are taken from Neuralangelo [Li et al. 2023] and the results of explicit methods are taken from 2DGS [Huang et al. 2024], where the mesh of 3DGS [Kerbl et al. 2023] and 2DGS [Huang et al. 2024] are extracted with TSDF fusion and SuGaR uses Poisson reconstruction.”
- Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians (2024, methodology): “3) Baselines: We compare our method against 2D-GS [15], 3D-GS [5], Scaffold-GS [3], Mip-Splatting [14] and two concurrent works, CityGaussian [19] and Hierarchical-GS [2].”
- Recent advances in 3D Gaussian splatting (2024, positive): “To avoid duplicate densifi-cation, SplaTAM [116] uses view-independent colors for Gaussians and creates a densification mask to determine whether a pixel in a new frame needs densification by considering current Gaussians and the captured depth of the new frame.”