MASt3R-Fusion: Integrating Feed-Forward Visual Model with IMU, GNSS for High-Functionality SLAM

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhou, Yuxuan, Li, Xingxing, Li, Shengyu, Yan, Zhuohao, Xia, Chunxi, Feng, Shaoquan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915619719348224
author Zhou, Yuxuan
Li, Xingxing
Li, Shengyu
Yan, Zhuohao
Xia, Chunxi
Feng, Shaoquan
author_facet Zhou, Yuxuan
Li, Xingxing
Li, Shengyu
Yan, Zhuohao
Xia, Chunxi
Feng, Shaoquan
contents Visual SLAM is a cornerstone technique in robotics, autonomous driving and extended reality (XR), yet classical systems often struggle with low-texture environments, scale ambiguity, and degraded performance under challenging visual conditions. Recent advancements in feed-forward neural network-based pointmap regression have demonstrated the potential to recover high-fidelity 3D scene geometry directly from images, leveraging learned spatial priors to overcome limitations of traditional multi-view geometry methods. However, the widely validated advantages of probabilistic multi-sensor information fusion are often discarded in these pipelines. In this work, we propose MASt3R-Fusion,a multi-sensor-assisted visual SLAM framework that tightly integrates feed-forward pointmap regression with complementary sensor information, including inertial measurements and GNSS data. The system introduces Sim(3)-based visualalignment constraints (in the Hessian form) into a universal metric-scale SE(3) factor graph for effective information fusion. A hierarchical factor graph design is developed, which allows both real-time sliding-window optimization and global optimization with aggressive loop closures, enabling real-time pose tracking, metric-scale structure perception and globally consistent mapping. We evaluate our approach on both public benchmarks and self-collected datasets, demonstrating substantial improvements in accuracy and robustness over existing visual-centered multi-sensor SLAM systems. The code will be released open-source to support reproducibility and further research (https://github.com/GREAT-WHU/MASt3R-Fusion).
format Preprint
id arxiv_https___arxiv_org_abs_2509_20757
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MASt3R-Fusion: Integrating Feed-Forward Visual Model with IMU, GNSS for High-Functionality SLAM
Zhou, Yuxuan
Li, Xingxing
Li, Shengyu
Yan, Zhuohao
Xia, Chunxi
Feng, Shaoquan
Robotics
Computer Vision and Pattern Recognition
Visual SLAM is a cornerstone technique in robotics, autonomous driving and extended reality (XR), yet classical systems often struggle with low-texture environments, scale ambiguity, and degraded performance under challenging visual conditions. Recent advancements in feed-forward neural network-based pointmap regression have demonstrated the potential to recover high-fidelity 3D scene geometry directly from images, leveraging learned spatial priors to overcome limitations of traditional multi-view geometry methods. However, the widely validated advantages of probabilistic multi-sensor information fusion are often discarded in these pipelines. In this work, we propose MASt3R-Fusion,a multi-sensor-assisted visual SLAM framework that tightly integrates feed-forward pointmap regression with complementary sensor information, including inertial measurements and GNSS data. The system introduces Sim(3)-based visualalignment constraints (in the Hessian form) into a universal metric-scale SE(3) factor graph for effective information fusion. A hierarchical factor graph design is developed, which allows both real-time sliding-window optimization and global optimization with aggressive loop closures, enabling real-time pose tracking, metric-scale structure perception and globally consistent mapping. We evaluate our approach on both public benchmarks and self-collected datasets, demonstrating substantial improvements in accuracy and robustness over existing visual-centered multi-sensor SLAM systems. The code will be released open-source to support reproducibility and further research (https://github.com/GREAT-WHU/MASt3R-Fusion).
title MASt3R-Fusion: Integrating Feed-Forward Visual Model with IMU, GNSS for High-Functionality SLAM
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.20757