Research demo Dataset 2024
VR.Net
A large-scale, real-world dataset for virtual-reality motion sickness research.
Placeholder
VR.Net is a large-scale, real-world dataset for studying virtual-reality motion sickness (cybersickness). Collected from commercial VR games across many participants, it pairs gameplay with labelled sickness signals — enabling machine-learning models that predict and help mitigate cybersickness. The work received the Best Paper Award at IEEE VR 2024.
What’s inside
- Real gameplay — recordings captured from commercial VR titles rather than contrived lab tasks, for ecological validity.
- Labelled sickness signals — synchronized cybersickness annotations aligned to the gameplay stream.
- Built for ML — structured so researchers can train and benchmark models that predict and mitigate motion sickness.
Access the dataset
The dataset is available to download via Google Drive — use the Download dataset link above. For the full methodology and results, see the related publication, VR.Net: A real-world dataset for virtual reality motion sickness research (IEEE TVCG / IEEE VR 2024).