CVGRDec 1, 2024

Ref-GS: Directional Factorization for 2D Gaussian Splatting

arXiv:2412.00905v226 citationsh-index: 12CVPR
Originality Incremental advance
AI Analysis

This work addresses rendering challenges in computer graphics for applications like virtual reality or simulation, but it appears incremental as it builds upon existing Gaussian splatting methods.

The paper tackled the problem of enabling photorealistic view-dependent appearance rendering and precise geometry recovery in 2D Gaussian splatting by introducing Ref-GS, which uses directional factorization and a spherical Mip-grid to reduce ambiguity and capture surface roughness, achieving superior rendering for open-world scenes.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes