3D Gaussian Splatting against Moving Objects for High-Fidelity Street Scene Reconstruction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zheng, Peizhen, Jiang, Dongjing, Jiao, Qingchong, Bouchtaoui, Redouane EL, Zhang, Flynnwell Jianfei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915972851433472
author Zheng, Peizhen
Jiang, Dongjing
Jiao, Qingchong
Bouchtaoui, Redouane EL
Zhang, Flynnwell Jianfei
author_facet Zheng, Peizhen
Jiang, Dongjing
Jiao, Qingchong
Bouchtaoui, Redouane EL
Zhang, Flynnwell Jianfei
contents The accurate reconstruction of dynamic street scenes is critical for applications in autonomous driving, augmented reality, and virtual reality. Traditional methods relying on dense point clouds and triangular meshes struggle with moving objects, occlusions, and real-time processing constraints, limiting their effectiveness in complex urban environments. While multi-view stereo and neural radiance fields have advanced 3D reconstruction, they face challenges in computational efficiency and handling scene dynamics. This paper proposes a novel 3D Gaussian point distribution method for dynamic street scene reconstruction. Our approach introduces an adaptive transparency mechanism that eliminates moving objects while preserving high-fidelity static scene details. Additionally, iterative refinement of Gaussian point distribution enhances geometric accuracy and texture representation. We integrate directional encoding with spatial position optimization to optimize storage and rendering efficiency, reducing redundancy while maintaining scene integrity. Experimental results demonstrate that our method achieves high reconstruction quality, improved rendering performance, and adaptability in large-scale dynamic environments. These contributions establish a robust framework for real-time, high-precision 3D reconstruction, advancing the practicality of dynamic scene modeling across multiple applications. The source code for this work is available to the public at https://github.com/okic-ca/3dgs
format Preprint
id arxiv_https___arxiv_org_abs_2503_12001
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle 3D Gaussian Splatting against Moving Objects for High-Fidelity Street Scene Reconstruction
Zheng, Peizhen
Jiang, Dongjing
Jiao, Qingchong
Bouchtaoui, Redouane EL
Zhang, Flynnwell Jianfei
Computer Vision and Pattern Recognition
The accurate reconstruction of dynamic street scenes is critical for applications in autonomous driving, augmented reality, and virtual reality. Traditional methods relying on dense point clouds and triangular meshes struggle with moving objects, occlusions, and real-time processing constraints, limiting their effectiveness in complex urban environments. While multi-view stereo and neural radiance fields have advanced 3D reconstruction, they face challenges in computational efficiency and handling scene dynamics. This paper proposes a novel 3D Gaussian point distribution method for dynamic street scene reconstruction. Our approach introduces an adaptive transparency mechanism that eliminates moving objects while preserving high-fidelity static scene details. Additionally, iterative refinement of Gaussian point distribution enhances geometric accuracy and texture representation. We integrate directional encoding with spatial position optimization to optimize storage and rendering efficiency, reducing redundancy while maintaining scene integrity. Experimental results demonstrate that our method achieves high reconstruction quality, improved rendering performance, and adaptability in large-scale dynamic environments. These contributions establish a robust framework for real-time, high-precision 3D reconstruction, advancing the practicality of dynamic scene modeling across multiple applications. The source code for this work is available to the public at https://github.com/okic-ca/3dgs
title 3D Gaussian Splatting against Moving Objects for High-Fidelity Street Scene Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.12001