Self-Supervised Deep Pose Corrections for Robust Visual Odometry
This work addresses robust visual odometry for robotics and autonomous systems, presenting an incremental improvement by building on prior data-driven correction methods.
The paper tackles the problem of improving visual odometry accuracy by introducing a self-supervised deep pose correction network that applies corrections to existing estimators, removing the need for ground truth data and often outperforming supervised methods, with experiments showing significant enhancements over classical and learning-only approaches.
We present a self-supervised deep pose correction (DPC) network that applies pose corrections to a visual odometry estimator to improve its accuracy. Instead of regressing inter-frame pose changes directly, we build on prior work that uses data-driven learning to regress pose corrections that account for systematic errors due to violations of modelling assumptions. Our self-supervised formulation removes any requirement for six-degrees-of-freedom ground truth and, in contrast to expectations, often improves overall navigation accuracy compared to a supervised approach. Through extensive experiments, we show that our self-supervised DPC network can significantly enhance the performance of classical monocular and stereo odometry estimators and substantially out-performs state-of-the-art learning-only approaches.