MDN-VO: Estimating Visual Odometry with Confidence
Nimet Kaygusuz,Oscar Mendez,Richard Bowden,Nimet Kaygusuz,Oscar Mendez,Richard Bowden
Visual Odometry (VO) is used in many applications including robotics and autonomous systems. However, traditional approaches based on feature matching are computationally expensive and do not directly address failure cases, instead relying on heuristic methods to detect failure. In this work, we propose a deep learning-based VO model to efficiently estimate 6-DoF poses, as well as a confidence mod...
