CVAug 7, 2024

3iGS: Factorised Tensorial Illumination for 3D Gaussian Splatting

arXiv:2408.03753v117 citationsh-index: 38
Originality Incremental advance
AI Analysis

This work addresses a specific bottleneck in novel view synthesis for computer graphics, offering an incremental improvement over 3DGS.

The paper tackles the problem of unsatisfactory view-dependent effects in 3D Gaussian Splatting (3DGS) by proposing 3iGS, which expresses outgoing radiance as a function of local illumination and BRDF features, resulting in significantly enhanced rendering quality for specular effects while maintaining fast training and rendering speeds.

The use of 3D Gaussians as representation of radiance fields has enabled high quality novel view synthesis at real-time rendering speed. However, the choice of optimising the outgoing radiance of each Gaussian independently as spherical harmonics results in unsatisfactory view dependent effects. In response to these limitations, our work, Factorised Tensorial Illumination for 3D Gaussian Splatting, or 3iGS, improves upon 3D Gaussian Splatting (3DGS) rendering quality. Instead of optimising a single outgoing radiance parameter, 3iGS enhances 3DGS view-dependent effects by expressing the outgoing radiance as a function of a local illumination field and Bidirectional Reflectance Distribution Function (BRDF) features. We optimise a continuous incident illumination field through a Tensorial Factorisation representation, while separately fine-tuning the BRDF features of each 3D Gaussian relative to this illumination field. Our methodology significantly enhances the rendering quality of specular view-dependent effects of 3DGS, while maintaining rapid training and rendering speeds.

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