Good Deep Features to Track: Self-Supervised Feature Extraction and Tracking in Visual Odometry
This work addresses visual-based localization for robotics or autonomous systems in large-scale, outdoor, and long-term settings, but it appears incremental as it builds on existing learning-based methods like SuperPoint and SuperGlue.
The paper tackles the problem of degraded feature extraction and tracking in visual odometry under challenging conditions like lighting changes and low-texture areas, resulting in improved generalization and reliability through self-supervised learning with task-specific feedback.
Visual-based localization has made significant progress, yet its performance often drops in large-scale, outdoor, and long-term settings due to factors like lighting changes, dynamic scenes, and low-texture areas. These challenges degrade feature extraction and tracking, which are critical for accurate motion estimation. While learning-based methods such as SuperPoint and SuperGlue show improved feature coverage and robustness, they still face generalization issues with out-of-distribution data. We address this by enhancing deep feature extraction and tracking through self-supervised learning with task specific feedback. Our method promotes stable and informative features, improving generalization and reliability in challenging environments.