SVGS: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Rui, Chen, Wenyue, Wang, Jiepeng, Liu, Yuan, Wang, Peng, Lin, Cheng, Xin, Shiqing, Li, Xin, Wang, Wenping, Komura, Taku
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915974543835136
author Xu, Rui
Chen, Wenyue
Wang, Jiepeng
Liu, Yuan
Wang, Peng
Lin, Cheng
Xin, Shiqing
Li, Xin
Wang, Wenping
Komura, Taku
author_facet Xu, Rui
Chen, Wenyue
Wang, Jiepeng
Liu, Yuan
Wang, Peng
Lin, Cheng
Xin, Shiqing
Li, Xin
Wang, Wenping
Komura, Taku
contents Gaussian Splatting demonstrates impressive results in multi-view reconstruction based on Gaussian explicit representations. However, the current Gaussian primitives only have a single view-dependent color and an opacity to represent the appearance and geometry of the scene, resulting in a non-compact representation. In this paper, we introduce a new method called SVGS (Spatially Varying Gaussian Splatting) that utilizes spatially varying colors and opacity in a single Gaussian primitive to improve its representation ability. We have implemented bilinear interpolation, movable kernels, and tiny neural networks as spatially varying functions. SVGS employs 2D Gaussian surfels as primitives, which significantly enhances novel-view synthesis while maintaining high-quality geometric reconstruction. This approach is particularly effective in practical applications, as scenes combining complex textures with relatively simple geometry occur frequently in real-world environments. Quantitative and qualitative experimental results demonstrate that all three functions outperform the baseline, with the best movable kernels achieving superior novel view synthesis performance on multiple datasets, highlighting the strong potential of spatially varying functions. Project page: https://ruixu.me/html/SuperGaussians/index.html
format Preprint
id arxiv_https___arxiv_org_abs_2411_18966
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SVGS: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors
Xu, Rui
Chen, Wenyue
Wang, Jiepeng
Liu, Yuan
Wang, Peng
Lin, Cheng
Xin, Shiqing
Li, Xin
Wang, Wenping
Komura, Taku
Computer Vision and Pattern Recognition
Graphics
Multimedia
Gaussian Splatting demonstrates impressive results in multi-view reconstruction based on Gaussian explicit representations. However, the current Gaussian primitives only have a single view-dependent color and an opacity to represent the appearance and geometry of the scene, resulting in a non-compact representation. In this paper, we introduce a new method called SVGS (Spatially Varying Gaussian Splatting) that utilizes spatially varying colors and opacity in a single Gaussian primitive to improve its representation ability. We have implemented bilinear interpolation, movable kernels, and tiny neural networks as spatially varying functions. SVGS employs 2D Gaussian surfels as primitives, which significantly enhances novel-view synthesis while maintaining high-quality geometric reconstruction. This approach is particularly effective in practical applications, as scenes combining complex textures with relatively simple geometry occur frequently in real-world environments. Quantitative and qualitative experimental results demonstrate that all three functions outperform the baseline, with the best movable kernels achieving superior novel view synthesis performance on multiple datasets, highlighting the strong potential of spatially varying functions. Project page: https://ruixu.me/html/SuperGaussians/index.html
title SVGS: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors
topic Computer Vision and Pattern Recognition
Graphics
Multimedia
url https://arxiv.org/abs/2411.18966