OccluGaussian: Occlusion-Aware Gaussian Splatting for Large Scene Reconstruction and Rendering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Shiyong, Tang, Xiao, Li, Zhihao, He, Yingfan, Ye, Chongjie, Liu, Jianzhuang, Huang, Binxiao, Zhou, Shunbo, Wu, Xiaofei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915644266512384
author Liu, Shiyong
Tang, Xiao
Li, Zhihao
He, Yingfan
Ye, Chongjie
Liu, Jianzhuang
Huang, Binxiao
Zhou, Shunbo
Wu, Xiaofei
author_facet Liu, Shiyong
Tang, Xiao
Li, Zhihao
He, Yingfan
Ye, Chongjie
Liu, Jianzhuang
Huang, Binxiao
Zhou, Shunbo
Wu, Xiaofei
contents In large-scale scene reconstruction using 3D Gaussian splatting, it is common to partition the scene into multiple smaller regions and reconstruct them individually. However, existing division methods are occlusion-agnostic, meaning that each region may contain areas with severe occlusions. As a result, the cameras within those regions are less correlated, leading to a low average contribution to the overall reconstruction. In this paper, we propose an occlusion-aware scene division strategy that clusters training cameras based on their positions and co-visibilities to acquire multiple regions. Cameras in such regions exhibit stronger correlations and a higher average contribution, facilitating high-quality scene reconstruction. We further propose a region-based rendering technique to accelerate large scene rendering, which culls Gaussians invisible to the region where the viewpoint is located. Such a technique significantly speeds up the rendering without compromising quality. Extensive experiments on multiple large scenes show that our method achieves superior reconstruction results with faster rendering speed compared to existing state-of-the-art approaches. Project page: https://occlugaussian.github.io.
format Preprint
id arxiv_https___arxiv_org_abs_2503_16177
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OccluGaussian: Occlusion-Aware Gaussian Splatting for Large Scene Reconstruction and Rendering
Liu, Shiyong
Tang, Xiao
Li, Zhihao
He, Yingfan
Ye, Chongjie
Liu, Jianzhuang
Huang, Binxiao
Zhou, Shunbo
Wu, Xiaofei
Graphics
Computer Vision and Pattern Recognition
In large-scale scene reconstruction using 3D Gaussian splatting, it is common to partition the scene into multiple smaller regions and reconstruct them individually. However, existing division methods are occlusion-agnostic, meaning that each region may contain areas with severe occlusions. As a result, the cameras within those regions are less correlated, leading to a low average contribution to the overall reconstruction. In this paper, we propose an occlusion-aware scene division strategy that clusters training cameras based on their positions and co-visibilities to acquire multiple regions. Cameras in such regions exhibit stronger correlations and a higher average contribution, facilitating high-quality scene reconstruction. We further propose a region-based rendering technique to accelerate large scene rendering, which culls Gaussians invisible to the region where the viewpoint is located. Such a technique significantly speeds up the rendering without compromising quality. Extensive experiments on multiple large scenes show that our method achieves superior reconstruction results with faster rendering speed compared to existing state-of-the-art approaches. Project page: https://occlugaussian.github.io.
title OccluGaussian: Occlusion-Aware Gaussian Splatting for Large Scene Reconstruction and Rendering
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.16177