Towards a Better Understanding of VR Sickness: Physical Symptom Prediction for VR Contents

We address the black-box issue of VR sickness assessment (VRSA) by evaluating level physical symptoms sickness. For contents inducing similar level, can vary depending on characteristics contents. Most existing VRSA methods focused assessing overall score. To make better understanding sickness, it is required to predict and provide major rather than degree In this paper, we degrees main affecting which are disorientation, nausea, oculomotor. addition, introduce a new large-scale dataset for including 360 videos with various frame rates, physiological signals, subjective scores. On benchmark our newly collected dataset, approach shows potential not only achieve highest correlation scores, but also understand causes