ExploreGS: a vision-based low overhead framework for 3D scene reconstruction

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Feng, Yunji, Yu, Chengpu, Ran, Fengrui, Yang, Zhi, Liu, Yinni
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912378943176704
author Feng, Yunji
Yu, Chengpu
Ran, Fengrui
Yang, Zhi
Liu, Yinni
author_facet Feng, Yunji
Yu, Chengpu
Ran, Fengrui
Yang, Zhi
Liu, Yinni
contents This paper proposes a low-overhead, vision-based 3D scene reconstruction framework for drones, named ExploreGS. By using RGB images, ExploreGS replaces traditional lidar-based point cloud acquisition process with a vision model, achieving a high-quality reconstruction at a lower cost. The framework integrates scene exploration and model reconstruction, and leverags a Bag-of-Words(BoW) model to enable real-time processing capabilities, therefore, the 3D Gaussian Splatting (3DGS) training can be executed on-board. Comprehensive experiments in both simulation and real-world environments demonstrate the efficiency and applicability of the ExploreGS framework on resource-constrained devices, while maintaining reconstruction quality comparable to state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2505_10578
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ExploreGS: a vision-based low overhead framework for 3D scene reconstruction
Feng, Yunji
Yu, Chengpu
Ran, Fengrui
Yang, Zhi
Liu, Yinni
Image and Video Processing
Computer Vision and Pattern Recognition
This paper proposes a low-overhead, vision-based 3D scene reconstruction framework for drones, named ExploreGS. By using RGB images, ExploreGS replaces traditional lidar-based point cloud acquisition process with a vision model, achieving a high-quality reconstruction at a lower cost. The framework integrates scene exploration and model reconstruction, and leverags a Bag-of-Words(BoW) model to enable real-time processing capabilities, therefore, the 3D Gaussian Splatting (3DGS) training can be executed on-board. Comprehensive experiments in both simulation and real-world environments demonstrate the efficiency and applicability of the ExploreGS framework on resource-constrained devices, while maintaining reconstruction quality comparable to state-of-the-art methods.
title ExploreGS: a vision-based low overhead framework for 3D scene reconstruction
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.10578