Deep 6-DOF Tracking
This addresses the need for reliable object tracking in computer vision applications, though it appears incremental as it builds on existing deep learning methods for tracking.
The paper tackles the problem of 6-DOF tracking in challenging real-world scenarios, achieving state-of-the-art performance with improved accuracy and robustness to occlusions while maintaining real-time speed.
We present a temporal 6-DOF tracking method which leverages deep learning to achieve state-of-the-art performance on challenging datasets of real world capture. Our method is both more accurate and more robust to occlusions than the existing best performing approaches while maintaining real-time performance. To assess its efficacy, we evaluate our approach on several challenging RGBD sequences of real objects in a variety of conditions. Notably, we systematically evaluate robustness to occlusions through a series of sequences where the object to be tracked is increasingly occluded. Finally, our approach is purely data-driven and does not require any hand-designed features: robust tracking is automatically learned from data.