Towards Consumer-Grade Cybersickness Prediction: Multi-Model Alignment for Real-Time Vision-Only Inference

TL;DR

This paper introduces a real-time, vision-only cybersickness prediction framework for consumer VR that uses multi-modal data and graph neural networks to achieve high accuracy without invasive sensors.

Contribution

The work presents a scalable, personalized cybersickness prediction model using only non-invasive signals and a novel multi-modal alignment approach, enabling real-time inference in consumer VR.

Findings

Achieves 88.4% accuracy in cybersickness prediction

Reduces deployment complexity compared to EEG-based methods

Supports real-time inference with 90ms latency

Abstract

Cybersickness remains a major obstacle to the widespread adoption of immersive virtual reality (VR), particularly in consumer-grade environments. While prior methods rely on invasive signals such as electroencephalography (EEG) for high predictive accuracy, these approaches require specialized hardware and are impractical for real-world applications. In this work, we propose a scalable, deployable framework for personalized cybersickness prediction leveraging only non-invasive signals readily available from commercial VR headsets, including head motion, eye tracking, and physiological responses. Our model employs a modality-specific graph neural network enhanced with a Difference Attention Module to extract temporal-spatial embeddings capturing dynamic changes across modalities. A cross-modal alignment module jointly trains the video encoder to learn personalized traits by aligning video features with sensor-derived representations. Consequently, the model accurately predicts individual cybersickness using only video input during inference. Experimental results show our model achieves 88.4\% accuracy, closely matching EEG-based approaches (89.16\%), while reducing deployment complexity. With an average inference latency of 90ms, our framework supports real-time applications, ideal for integration into consumer-grade VR platforms without compromising personalization or performance. The code will be relesed at https://github.com/U235-Aurora/PTGNN.