Ref-GS: Directional Factorization for 2D Gaussian Splatting

Abstract

In this paper, we introduce Ref-GS, a novel approach for directional light factorization in 2D Gaussian splatting, which enables photorealistic view-dependent appearance rendering and precise geometry recovery. Ref-GS builds upon the deferred rendering of Gaussian splatting and applies directional encoding to the deferred-rendered surface, effectively reducing the ambiguity between orientation and viewing angle. Next, we introduce a spherical mip-grid to capture varying levels of surface roughness, enabling roughness-aware Gaussian shading. Additionally, we propose a simple yet efficient geometry-lighting factorization that connects geometry and lighting via the vector outer product, significantly reducing renderer overhead when integrating volumetric attributes. Our method achieves superior photorealistic rendering for a range of open-world scenes while also accurately recovering geometry.

Cite

Text

Zhang et al. "Ref-GS: Directional Factorization for 2D Gaussian Splatting." Conference on Computer Vision and Pattern Recognition, 2025. doi:10.1109/CVPR52734.2025.02466

Markdown

[Zhang et al. "Ref-GS: Directional Factorization for 2D Gaussian Splatting." Conference on Computer Vision and Pattern Recognition, 2025.](https://mlanthology.org/cvpr/2025/zhang2025cvpr-refgs/) doi:10.1109/CVPR52734.2025.02466

BibTeX

@inproceedings{zhang2025cvpr-refgs,
  title     = {{Ref-GS: Directional Factorization for 2D Gaussian Splatting}},
  author    = {Zhang, Youjia and Chen, Anpei and Wan, Yumin and Song, Zikai and Yu, Junqing and Luo, Yawei and Yang, Wei},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2025},
  pages     = {26483-26492},
  doi       = {10.1109/CVPR52734.2025.02466},
  url       = {https://mlanthology.org/cvpr/2025/zhang2025cvpr-refgs/}
}