Ref-GS: Directional Factorization for 2D Gaussian Splatting
Youjia Zhang, Anpei Chen, Yumin Wan, Zikai Song, Junqing Yu, Yawei, Luo, Wei Yang

TL;DR
Ref-GS introduces a directional factorization technique for 2D Gaussian splatting that enhances photorealistic, view-dependent rendering and accurate geometry recovery by incorporating directional encoding, surface roughness, and efficient geometry-lighting factorization.
Contribution
The paper presents a novel directional encoding and a spherical Mip-grid for Gaussian splatting, improving realism and geometry accuracy in view-dependent rendering.
Findings
Achieves superior photorealistic rendering in open-world scenes.
Effectively recovers geometry with high accuracy.
Reduces renderer overhead through efficient geometry-lighting factorization.
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsFace and Expression Recognition · Video Surveillance and Tracking Methods
