GS-LTS: 3D Gaussian Splatting-Based Adaptive Modeling for Long-Term Service Robots

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fu, Bin, Li, Jialin, Zhang, Bin, Wang, Ruiping, Chen, Xilin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908279670571008
author Fu, Bin
Li, Jialin
Zhang, Bin
Wang, Ruiping
Chen, Xilin
author_facet Fu, Bin
Li, Jialin
Zhang, Bin
Wang, Ruiping
Chen, Xilin
contents 3D Gaussian Splatting (3DGS) has garnered significant attention in robotics for its explicit, high fidelity dense scene representation, demonstrating strong potential for robotic applications. However, 3DGS-based methods in robotics primarily focus on static scenes, with limited attention to the dynamic scene changes essential for long-term service robots. These robots demand sustained task execution and efficient scene updates-challenges current approaches fail to meet. To address these limitations, we propose GS-LTS (Gaussian Splatting for Long-Term Service), a 3DGS-based system enabling indoor robots to manage diverse tasks in dynamic environments over time. GS-LTS detects scene changes (e.g., object addition or removal) via single-image change detection, employs a rule-based policy to autonomously collect multi-view observations, and efficiently updates the scene representation through Gaussian editing. Additionally, we propose a simulation-based benchmark that automatically generates scene change data as compact configuration scripts, providing a standardized, user-friendly evaluation benchmark. Experimental results demonstrate GS-LTS's advantages in reconstruction, navigation, and superior scene updates-faster and higher quality than the image training baseline-advancing 3DGS for long-term robotic operations. Code and benchmark are available at: https://vipl-vsu.github.io/3DGS-LTS.
format Preprint
id arxiv_https___arxiv_org_abs_2503_17733
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GS-LTS: 3D Gaussian Splatting-Based Adaptive Modeling for Long-Term Service Robots
Fu, Bin
Li, Jialin
Zhang, Bin
Wang, Ruiping
Chen, Xilin
Robotics
Computer Vision and Pattern Recognition
3D Gaussian Splatting (3DGS) has garnered significant attention in robotics for its explicit, high fidelity dense scene representation, demonstrating strong potential for robotic applications. However, 3DGS-based methods in robotics primarily focus on static scenes, with limited attention to the dynamic scene changes essential for long-term service robots. These robots demand sustained task execution and efficient scene updates-challenges current approaches fail to meet. To address these limitations, we propose GS-LTS (Gaussian Splatting for Long-Term Service), a 3DGS-based system enabling indoor robots to manage diverse tasks in dynamic environments over time. GS-LTS detects scene changes (e.g., object addition or removal) via single-image change detection, employs a rule-based policy to autonomously collect multi-view observations, and efficiently updates the scene representation through Gaussian editing. Additionally, we propose a simulation-based benchmark that automatically generates scene change data as compact configuration scripts, providing a standardized, user-friendly evaluation benchmark. Experimental results demonstrate GS-LTS's advantages in reconstruction, navigation, and superior scene updates-faster and higher quality than the image training baseline-advancing 3DGS for long-term robotic operations. Code and benchmark are available at: https://vipl-vsu.github.io/3DGS-LTS.
title GS-LTS: 3D Gaussian Splatting-Based Adaptive Modeling for Long-Term Service Robots
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.17733