MetaTOC stay on top of your field, easily

A transformer-enhanced geometric learning framework for robust monocular visual odometry

, , , , ,

Transactions of the Institute of Measurement and Control

Published online on

Abstract

Transactions of the Institute of Measurement and Control, Ahead of Print.
Monocular visual odometry (VO) is crucial for ego-motion estimation in autonomous systems, but it suffers from scale ambiguity, computational inefficiencies, and poor generalization across different motion scales. In this paper, we introduce a novel end-...