GStex: Per-Primitive Texturing of 2D Gaussian Splatting for Decoupled Appearance and Geometry Modeling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rong, Victor, Chen, Jingxiang, Bahmani, Sherwin, Kutulakos, Kiriakos N., Lindell, David B.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910846087593984
author Rong, Victor
Chen, Jingxiang
Bahmani, Sherwin
Kutulakos, Kiriakos N.
Lindell, David B.
author_facet Rong, Victor
Chen, Jingxiang
Bahmani, Sherwin
Kutulakos, Kiriakos N.
Lindell, David B.
contents Gaussian splatting has demonstrated excellent performance for view synthesis and scene reconstruction. The representation achieves photorealistic quality by optimizing the position, scale, color, and opacity of thousands to millions of 2D or 3D Gaussian primitives within a scene. However, since each Gaussian primitive encodes both appearance and geometry, these attributes are strongly coupled--thus, high-fidelity appearance modeling requires a large number of Gaussian primitives, even when the scene geometry is simple (e.g., for a textured planar surface). We propose to texture each 2D Gaussian primitive so that even a single Gaussian can be used to capture appearance details. By employing per-primitive texturing, our appearance representation is agnostic to the topology and complexity of the scene's geometry. We show that our approach, GStex, yields improved visual quality over prior work in texturing Gaussian splats. Furthermore, we demonstrate that our decoupling enables improved novel view synthesis performance compared to 2D Gaussian splatting when reducing the number of Gaussian primitives, and that GStex can be used for scene appearance editing and re-texturing.
format Preprint
id arxiv_https___arxiv_org_abs_2409_12954
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GStex: Per-Primitive Texturing of 2D Gaussian Splatting for Decoupled Appearance and Geometry Modeling
Rong, Victor
Chen, Jingxiang
Bahmani, Sherwin
Kutulakos, Kiriakos N.
Lindell, David B.
Computer Vision and Pattern Recognition
Graphics
I.3; I.4
Gaussian splatting has demonstrated excellent performance for view synthesis and scene reconstruction. The representation achieves photorealistic quality by optimizing the position, scale, color, and opacity of thousands to millions of 2D or 3D Gaussian primitives within a scene. However, since each Gaussian primitive encodes both appearance and geometry, these attributes are strongly coupled--thus, high-fidelity appearance modeling requires a large number of Gaussian primitives, even when the scene geometry is simple (e.g., for a textured planar surface). We propose to texture each 2D Gaussian primitive so that even a single Gaussian can be used to capture appearance details. By employing per-primitive texturing, our appearance representation is agnostic to the topology and complexity of the scene's geometry. We show that our approach, GStex, yields improved visual quality over prior work in texturing Gaussian splats. Furthermore, we demonstrate that our decoupling enables improved novel view synthesis performance compared to 2D Gaussian splatting when reducing the number of Gaussian primitives, and that GStex can be used for scene appearance editing and re-texturing.
title GStex: Per-Primitive Texturing of 2D Gaussian Splatting for Decoupled Appearance and Geometry Modeling
topic Computer Vision and Pattern Recognition
Graphics
I.3; I.4
url https://arxiv.org/abs/2409.12954