WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zheng, Jianhao, Zhu, Zihan, Bieri, Valentin, Pollefeys, Marc, Peng, Songyou, Armeni, Iro
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917977397395456
author Zheng, Jianhao
Zhu, Zihan
Bieri, Valentin
Pollefeys, Marc
Peng, Songyou
Armeni, Iro
author_facet Zheng, Jianhao
Zhu, Zihan
Bieri, Valentin
Pollefeys, Marc
Peng, Songyou
Armeni, Iro
contents We present WildGS-SLAM, a robust and efficient monocular RGB SLAM system designed to handle dynamic environments by leveraging uncertainty-aware geometric mapping. Unlike traditional SLAM systems, which assume static scenes, our approach integrates depth and uncertainty information to enhance tracking, mapping, and rendering performance in the presence of moving objects. We introduce an uncertainty map, predicted by a shallow multi-layer perceptron and DINOv2 features, to guide dynamic object removal during both tracking and mapping. This uncertainty map enhances dense bundle adjustment and Gaussian map optimization, improving reconstruction accuracy. Our system is evaluated on multiple datasets and demonstrates artifact-free view synthesis. Results showcase WildGS-SLAM's superior performance in dynamic environments compared to state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2504_03886
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments
Zheng, Jianhao
Zhu, Zihan
Bieri, Valentin
Pollefeys, Marc
Peng, Songyou
Armeni, Iro
Computer Vision and Pattern Recognition
Robotics
We present WildGS-SLAM, a robust and efficient monocular RGB SLAM system designed to handle dynamic environments by leveraging uncertainty-aware geometric mapping. Unlike traditional SLAM systems, which assume static scenes, our approach integrates depth and uncertainty information to enhance tracking, mapping, and rendering performance in the presence of moving objects. We introduce an uncertainty map, predicted by a shallow multi-layer perceptron and DINOv2 features, to guide dynamic object removal during both tracking and mapping. This uncertainty map enhances dense bundle adjustment and Gaussian map optimization, improving reconstruction accuracy. Our system is evaluated on multiple datasets and demonstrates artifact-free view synthesis. Results showcase WildGS-SLAM's superior performance in dynamic environments compared to state-of-the-art methods.
title WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2504.03886