Salient Sparse Visual Odometry With Pose-Only Supervision
This work addresses the challenge of accurate and robust visual odometry for autonomous systems in variable conditions, offering an incremental improvement over existing methods by reducing labeling needs.
The paper tackles the problem of visual odometry for autonomous navigation by proposing a hybrid framework that uses pose-only supervision to improve robustness and generalization without dense optical flow labels, achieving competitive performance on standard datasets and greater robustness in extreme scenarios.
Visual Odometry (VO) is vital for the navigation of autonomous systems, providing accurate position and orientation estimates at reasonable costs. While traditional VO methods excel in some conditions, they struggle with challenges like variable lighting and motion blur. Deep learning-based VO, though more adaptable, can face generalization problems in new environments. Addressing these drawbacks, this paper presents a novel hybrid visual odometry (VO) framework that leverages pose-only supervision, offering a balanced solution between robustness and the need for extensive labeling. We propose two cost-effective and innovative designs: a self-supervised homographic pre-training for enhancing optical flow learning from pose-only labels and a random patch-based salient point detection strategy for more accurate optical flow patch extraction. These designs eliminate the need for dense optical flow labels for training and significantly improve the generalization capability of the system in diverse and challenging environments. Our pose-only supervised method achieves competitive performance on standard datasets and greater robustness and generalization ability in extreme and unseen scenarios, even compared to dense optical flow-supervised state-of-the-art methods.