Textured Gaussians for Enhanced 3D Scene Appearance Modeling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chao, Brian, Tseng, Hung-Yu, Porzi, Lorenzo, Gao, Chen, Li, Tuotuo, Li, Qinbo, Saraf, Ayush, Huang, Jia-Bin, Kopf, Johannes, Wetzstein, Gordon, Kim, Changil
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914076934799360
author Chao, Brian
Tseng, Hung-Yu
Porzi, Lorenzo
Gao, Chen
Li, Tuotuo
Li, Qinbo
Saraf, Ayush
Huang, Jia-Bin
Kopf, Johannes
Wetzstein, Gordon
Kim, Changil
author_facet Chao, Brian
Tseng, Hung-Yu
Porzi, Lorenzo
Gao, Chen
Li, Tuotuo
Li, Qinbo
Saraf, Ayush
Huang, Jia-Bin
Kopf, Johannes
Wetzstein, Gordon
Kim, Changil
contents 3D Gaussian Splatting (3DGS) has recently emerged as a state-of-the-art 3D reconstruction and rendering technique due to its high-quality results and fast training and rendering time. However, pixels covered by the same Gaussian are always shaded in the same color up to a Gaussian falloff scaling factor. Furthermore, the finest geometric detail any individual Gaussian can represent is a simple ellipsoid. These properties of 3DGS greatly limit the expressivity of individual Gaussian primitives. To address these issues, we draw inspiration from texture and alpha mapping in traditional graphics and integrate it with 3DGS. Specifically, we propose a new generalized Gaussian appearance representation that augments each Gaussian with alpha~(A), RGB, or RGBA texture maps to model spatially varying color and opacity across the extent of each Gaussian. As such, each Gaussian can represent a richer set of texture patterns and geometric structures, instead of just a single color and ellipsoid as in naive Gaussian Splatting. Surprisingly, we found that the expressivity of Gaussians can be greatly improved by using alpha-only texture maps, and further augmenting Gaussians with RGB texture maps achieves the highest expressivity. We validate our method on a wide variety of standard benchmark datasets and our own custom captures at both the object and scene levels. We demonstrate image quality improvements over existing methods while using a similar or lower number of Gaussians.
format Preprint
id arxiv_https___arxiv_org_abs_2411_18625
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Textured Gaussians for Enhanced 3D Scene Appearance Modeling
Chao, Brian
Tseng, Hung-Yu
Porzi, Lorenzo
Gao, Chen
Li, Tuotuo
Li, Qinbo
Saraf, Ayush
Huang, Jia-Bin
Kopf, Johannes
Wetzstein, Gordon
Kim, Changil
Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
Image and Video Processing
3D Gaussian Splatting (3DGS) has recently emerged as a state-of-the-art 3D reconstruction and rendering technique due to its high-quality results and fast training and rendering time. However, pixels covered by the same Gaussian are always shaded in the same color up to a Gaussian falloff scaling factor. Furthermore, the finest geometric detail any individual Gaussian can represent is a simple ellipsoid. These properties of 3DGS greatly limit the expressivity of individual Gaussian primitives. To address these issues, we draw inspiration from texture and alpha mapping in traditional graphics and integrate it with 3DGS. Specifically, we propose a new generalized Gaussian appearance representation that augments each Gaussian with alpha~(A), RGB, or RGBA texture maps to model spatially varying color and opacity across the extent of each Gaussian. As such, each Gaussian can represent a richer set of texture patterns and geometric structures, instead of just a single color and ellipsoid as in naive Gaussian Splatting. Surprisingly, we found that the expressivity of Gaussians can be greatly improved by using alpha-only texture maps, and further augmenting Gaussians with RGB texture maps achieves the highest expressivity. We validate our method on a wide variety of standard benchmark datasets and our own custom captures at both the object and scene levels. We demonstrate image quality improvements over existing methods while using a similar or lower number of Gaussians.
title Textured Gaussians for Enhanced 3D Scene Appearance Modeling
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
Image and Video Processing
url https://arxiv.org/abs/2411.18625