English

Ref-GS: Directional Factorization for 2D Gaussian Splatting

Computer Vision and Pattern Recognition 2025-04-15 v2 Graphics

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.

Keywords

Cite

@article{arxiv.2412.00905,
  title  = {Ref-GS: Directional Factorization for 2D Gaussian Splatting},
  author = {Youjia Zhang and Anpei Chen and Yumin Wan and Zikai Song and Junqing Yu and Yawei Luo and Wei Yang},
  journal= {arXiv preprint arXiv:2412.00905},
  year   = {2025}
}

Comments

CVPR 2025. Project page: https://ref-gs.github.io/

R2 v1 2026-06-28T20:18:44.766Z