让2D高斯点云更真实地呈现光照方向与材质细节。
Ref-GS: Directional Factorization for 2D Gaussian Splatting
- 通过方向编码解决视角与法向混淆问题。
- 用球面Mip-grid捕捉不同粗糙度，实现材质感知着色。
- 用向量外积解耦几何与光照，提升渲染效率。
本文提出Ref-GS，一种用于2D高斯点云的定向光分解方法，可实现逼真的视图依赖外观渲染并精确恢复几何结构。Ref-GS基于高斯点云的延迟渲染机制，在延迟渲染的表面应用方向编码，有效缓解了法向与视角之间的歧义。我们引入球面Mip-grid以捕捉不同层次的表面粗糙度，实现粗糙度感知的高斯着色。此外，提出一种简单高效的几何-光照解耦方法，通过向量外积关联几何与光照信息，在整合体素属性时显著降低渲染开销。该方法在多种开放世界场景中均实现了卓越的逼真渲染效果，并能准确重建几何结构。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。