From 27e267177bce832ab1a768177a8a9c01cd6b32e7 Mon Sep 17 00:00:00 2001 From: Florian Barthel Date: Tue, 14 May 2024 18:47:05 +0200 Subject: [PATCH] update abstract --- project-page/index.html | 43 +++++++++++++++++++++++------------------ 1 file changed, 24 insertions(+), 19 deletions(-) diff --git a/project-page/index.html b/project-page/index.html index 1272dca..56d90ea 100644 --- a/project-page/index.html +++ b/project-page/index.html @@ -3,19 +3,23 @@ - + - + - + - + Self-Organizing Gaussian Splats Project Page @@ -134,21 +138,22 @@

Abstract

- 3D Gaussian Splatting has recently emerged as a highly promising technique for modeling of static 3D - scenes. In contrast to Neural Radiance Fields, it utilizes efficient rasterization allowing for very fast - rendering at high-quality. However, the storage size is significantly higher, which hinders practical - deployment, e.g.on resource constrained devices. In this paper, we introduce a compact scene - representation organizing the parameters of 3D Gaussian Splatting (3DGS) into a 2D grid with local - homogeneity, ensuring a drastic reduction in storage requirements without compromising visual quality - during rendering. Central to our idea is the explicit exploitation of perceptual redundancies present in - natural scenes. In essence, the inherent nature of a scene allows for numerous permutations of Gaussian - parameters to equivalently represent it. To this end, we propose a novel highly parallel algorithm that - regularly arranges the high-dimensional Gaussian parameters into a 2D grid while preserving their - neighborhood structure. During training, we further enforce local smoothness between the sorted parameters - in the grid. The uncompressed Gaussians use the same structure as 3DGS, ensuring a seamless integration - with established renderers. Our method achieves a reduction factor of 8x to 26x in size for complex scenes - with no increase in training time, marking a substantial leap forward in the domain of 3D scene - distribution and consumption. + 3D Gaussian Splatting has recently emerged as a highly promising technique for modeling of + static 3D scenes. In contrast to Neural Radiance Fields, it utilizes efficient rasterization + allowing for very fast rendering at high-quality. However, the storage size is significantly + higher, which hinders practical deployment, e.g.~on resource constrained devices. In this paper, + we introduce a compact scene representation organizing the parameters of 3D Gaussian Splatting + (3DGS) into a 2D grid with local homogeneity, ensuring a drastic reduction in storage + requirements without compromising visual quality during rendering. + Central to our idea is the explicit exploitation of perceptual redundancies present in natural + scenes. In essence, the inherent nature of a scene allows for numerous permutations of Gaussian + parameters to equivalently represent it. To this end, we propose a novel highly parallel + algorithm that regularly arranges the high-dimensional Gaussian parameters into a 2D grid while + preserving their neighborhood structure. During training, we further enforce local smoothness + between the sorted parameters in the grid. The uncompressed Gaussians use the same structure as + 3DGS, ensuring a seamless integration with established renderers. Our method achieves a + reduction factor of 17x to 42x in size for complex scenes with no increase in training time, + marking a substantial leap forward in the domain of 3D scene distribution and consumption.