SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting

Abstract

Surface reconstruction and novel view rendering from sparse-view images are challenging. Signed Distance Function (SDF)-based methods struggle with fine details, while 3D Gaussian Splatting (3DGS)-based approaches lack global geometry coherence. We propose a novel hybrid method that combines both strengths: SDF captures coarse geometry to enhance 3DGS-based rendering, while newly rendered images from 3DGS refine SDF details for accurate surface reconstruction. As a result, our method surpasses state-of-the-art approaches in surface reconstruction and novel view synthesis on DTU and MobileBrick datasets. Code will be released at https://github.com/aim-uofa/SurfaceSplat.

Cite

Text

Gao et al. "SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting." International Conference on Computer Vision, 2025.

Markdown

[Gao et al. "SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting." International Conference on Computer Vision, 2025.](https://mlanthology.org/iccv/2025/gao2025iccv-surfacesplat/)

BibTeX

@inproceedings{gao2025iccv-surfacesplat,
  title     = {{SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting}},
  author    = {Gao, Zihui and Bian, Jia-Wang and Lin, Guosheng and Chen, Hao and Shen, Chunhua},
  booktitle = {International Conference on Computer Vision},
  year      = {2025},
  pages     = {28525-28534},
  url       = {https://mlanthology.org/iccv/2025/gao2025iccv-surfacesplat/}
}