Volumetrically Consistent 3D Gaussian Rasterization

TL;DR

This paper introduces a volumetrically consistent 3D Gaussian rasterization method that improves physical accuracy and view synthesis quality by analytically integrating 3D Gaussians, outperforming previous splatting-based approaches.

Contribution

It replaces splatting approximations with direct volumetric integration of 3D Gaussians, enhancing physical accuracy and enabling applications like tomography.

Findings

Outperforms 3DGS in view synthesis metrics (SSIM, LPIPS)

Achieves higher accuracy with fewer points for opaque surfaces

Works effectively for tomography with fewer points

Abstract

Recently, 3D Gaussian Splatting (3DGS) has enabled photorealistic view synthesis at high inference speeds. However, its splatting-based rendering model makes several approximations to the rendering equation, reducing physical accuracy. We show that the core approximations in splatting are unnecessary, even within a rasterizer; We instead volumetrically integrate 3D Gaussians directly to compute the transmittance across them analytically. We use this analytic transmittance to derive more physically-accurate alpha values than 3DGS, which can directly be used within their framework. The result is a method that more closely follows the volume rendering equation (similar to ray-tracing) while enjoying the speed benefits of rasterization. Our method represents opaque surfaces with higher accuracy and fewer points than 3DGS. This enables it to outperform 3DGS for view synthesis (measured in SSIM and LPIPS). Being volumetrically consistent also enables our method to work out of the box for tomography. We match the state-of-the-art 3DGS-based tomography method with fewer points. Our code is publicly available at: https://github.com/chinmay0301ucsd/Vol3DGS