Accurate motion tracking in head-mounted displays (HMDs) has been widely used in immersive VR interaction technologies. However, tracking the head motion of users at all times is not always desirable. During a session of HMD usage, users may make scene-irrelevant head rotations, such as adjusting the head position to avoid neck pain or responding to distractions from the physical world. To the best of our knowledge, this is the first study that addresses the problem of scene-irrelevant head movements. We trained a classifier to detect scene-irrelevant motions using temporal eyehead-coordinated information sequences. To investigate the usefulness of the detection results, we propose a technique to suspend motion tracking in HMDs where scene-irrelevant motions are detected. /Conclusions Experimental results demonstrate that the scene-relevancy of movements can be detected using eye-head coordination information, and that ignoring scene-irrelevant head motions in HMDs improves user continuity without increasing sickness or breaking immersion.

In this paper, we propose a scale-aware method for inserting virtual objects with proper sizes into monocular videos. To tackle the scale ambiguity problem of geometry recovery from monocular videos, we estimate the global scale objects in a video with a Bayesian approach incorporating the size priors of objects, where the scene objects sizes should strictly conform to the same global scale and the possibilities of global scales are maximized according to the size distribution of object categories. To do so, we propose a dataset of sizes of object categories: Metric-Tree, a hierarchical representation of sizes of more than 900 object categories with the corresponding images. To handle the incompleteness of objects recovered from videos, we propose a novel scale estimation method that extracts plausible dimensions of objects for scale optimization. Experiments have shown that our method for scale estimation performs better than the state-of-the-art methods, and has considerable validity and robustness for different video scenes. Metric-Tree has been made available at: https://metric-tree.github.io