Egocentric 6-DoF Tracking of Small Handheld Objects
This addresses the problem of real-time pose tracking for VR/AR systems, but it is incremental as it builds on existing tracking methods with new data and constraints.
The paper tackles efficient 6-DoF tracking of handheld controllers from egocentric camera perspectives, achieving a mean average error of 33.5 millimeters in 3D keypoint prediction using the SSD-AF-Stereo3D model on the HMD Controller dataset.
Virtual and augmented reality technologies have seen significant growth in the past few years. A key component of such systems is the ability to track the pose of head mounted displays and controllers in 3D space. We tackle the problem of efficient 6-DoF tracking of a handheld controller from egocentric camera perspectives. We collected the HMD Controller dataset which consist of over 540,000 stereo image pairs labelled with the full 6-DoF pose of the handheld controller. Our proposed SSD-AF-Stereo3D model achieves a mean average error of 33.5 millimeters in 3D keypoint prediction and is used in conjunction with an IMU sensor on the controller to enable 6-DoF tracking. We also present results on approaches for model based full 6-DoF tracking. All our models operate under the strict constraints of real time mobile CPU inference.