Robotic Characterization of Markerless Hand-Tracking on Meta Quest Pro and Quest 3 Virtual Reality Headsets

Markerless hand-tracking has become increasingly common on commercially available virtual and mixed reality headsets to improve the naturalness of interaction and immersivity of virtual environments. However, there has been limited examination of the performance of markerless hand-tracking on commercial head-mounted displays. Here, we propose an evaluation methodology that leverages a robotic manipulator to measure the positional accuracy, jitter, and latency of such systems and provides a standardized characterization framework of markerless hand-tracking. We apply this methodology to evaluate the hand-tracking performance of two recent mixed reality devices from Meta: the Quest Pro and Quest 3. Results demonstrate the influence of proximity to the headset, rotation of hand, and joint selected as the tracking feature on hand-tracking performance. We found that hand-tracking error and jitter were lowest for both headsets in conditions where the knuckle was the tracking point compared to the fingertip. Regarding positional accuracy, in best-performing conditions, the Quest Pro outperformed the Quest 3 with 1.22 cm of average error compared to 1.73 cm. The opposite result was true concerning jitter, with results of 1.77 cm and 1.11 cm for the Quest Pro and Quest 3, respectively. We found latency highly variable for the Quest Pro (15.8 - 229.2 ms) and Quest 3 (14.4 - 220.5 ms). This work provides a testing framework for highly systematic and repeatable performance measurements of markerless hand-tracking systems embedded in headsets.

Our experimental setup integrates a KUKA LBR iiwa 7 R800 robot manipulator, a virtual reality headset (both Meta Quest Pro and Quest 3 within the following tests), a motion capture system serving as the ground-truth, and a custom hand model with embedded retroflective markers. This enables systematic and repeatable evaluation of the markerless hand-tracking embedded within commercial virtual reality headsets.

This test evaluates hand-tracking accuracy under static conditions, isolating measurement performance from the effects of latency. In this configuration, the hand remains stationary between frames, providing the optimal tracking scenario—free from temporal variation—and presenting a consistent view to the HMD cameras. This stability simplifies the identification process within the tracking algorithm. The evaluation workspace consisted of 147 test points: seven planar positions across three vertical levels, each combined with seven hand rotations. Both headsets were assessed using two anatomical reference modes, tracking centered on either the index knuckle or the index fingertip. At each unique point, two metrics were computed: the average Euclidean error, quantifying spatial deviation, and the sample-to-sample jitter, representing temporal noise within the tracking data. Regarding positional accuracy, in best-performing conditions, the Quest Pro outperformed the Quest 3 with 1.22 cm of average error compared to 1.73 cm. The opposite result was true concerning jitter, with results of 1.77 cm and 1.11 cm for the Quest Pro and Quest 3, respectively.

While implementing hand-tracking in virtual experiences is an important step forward, consistent and ongoing evaluations are necessary to properly characterize and document the progress of this technology for applications requiring accurate and precise hand pose data. This has motivated us to develop a repeatable and extensible process of markerless hand-tracking characterization within this work to not only facilitate the evaluation of current commercial headsets but also to lay the foundation for future testing and comparison.