Salient Sparse Visual Odometry With Pose-Only Supervision

arXiv:2404.04677v1 Announce Type: new
Abstract: Visual Odometry (VO) is vital for the navigation of autonomous systems, providing accurate position and orientation estimates at reasonable costs. While traditional VO methods excel in some conditions, they struggle with challenges like variable lighting and motion blur. Deep learning-based VO, though more adaptable, can face generalization problems in new environments. Addressing these drawbacks, this paper presents a novel hybrid visual odometry (VO) framework that leverages pose-only supervision, offering a balanced solution between robustness and …

abstract arxiv autonomous autonomous systems challenges costs cs.cv cs.ro deep learning excel face lighting navigation struggle supervision systems type visual vital