Dense mapping from sparse visual odometry: a lightweight uncertainty-guaranteed depth completion method

IntroductionVisual odometry (VO) has been widely deployed on mobile robots for spatial perception. State-of-the-art VO offers robust localization, the maps it generates are often too sparse for downstream tasks due to insufffcient depth data. While depth completion methods can estimate dense depth f...

詳細記述

書誌詳細

出版年:	Frontiers in Robotics and AI
主要な著者:	Daolong Yang, Xudong Zhang, Haoyuan Liu, Haoyang Wu, Chengcai Wang, Kun Xu, Xilun Ding
フォーマット:	論文
言語:	英語
出版事項:	Frontiers Media S.A. 2025-09-01
主題:	mapping deep learning for visual perception visual odometry depth completion uncertainty estimation
オンライン･アクセス:	https://www.frontiersin.org/articles/10.3389/frobt.2025.1644230/full