Fast and reliable 6D pose tracking method for rigid objects
Fast Pose Tracking of Rigid Objects with Compact Pose Graph Optimization
Computer Vision and Pattern Recognition
Summary
Tracking the exact position and orientation of objects over time is important in robotics and augmented reality but can be slow or require complicated setups. The authors developed a lightweight method that keeps track of an object’s movements accurately without heavy calculations by focusing on relative poses instead of detailed point matches. This keeps errors from adding up and allows for fast and reliable tracking over long periods. Their method works well on real-world tests and uses much less computing power than older methods.
What this means in practice
- •For robotic system builders: Enable real-time object pose tracking in robotic manipulation without heavy setup or slow computations.
- •For augmented reality developers: Integrate fast and robust 6D pose tracking of objects for interactive AR experiences that stay accurate over time.
Authors
Xiaojie Zhang, Tom Fischer, Viktor Larsson, Eddy Ilg
Abstract
Tracking a novel object's 6D pose over long horizons currently requires either expensive onboarding or a reconstruction maintained throughout the sequence. This makes current trackers impractical for robotic manipulation and augmented reality, which need trackers that are ready to use and run in real time. We show that a lightweight tracking module can be applied on top of a wide range of correspondence estimation methods to keep drifts bounded while maintaining fast runtime. Our key idea is to avoid point-based optimization in the pose graph and operate only on relative pose constraints, which we weight by a derived uncertainty from the geometric alignment. This makes optimization independent of the number of correspondences while avoiding the direct inclusion of noisy point measurements, leading to fast and robust long-term tracking. Across four real-world benchmarks, our approach achieves tracking accuracy comparable to reconstruction-based trackers with a fraction of the optimization cost. Overall, these results suggest that a compact and reliable pose graph optimization can provide long-horizon consistency at substantially lower computational cost.