Flow-Aware Diffusion for Real-Time VR Restoration: Mitigating Cybersickness With Enhanced Spatiotemporal Coherence
- 26 May 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (8) , 7486-7499
Abstract
Cybersickness remains a critical barrier to the widespread adoption of Virtual Reality (VR), particularly in scenarios involving intense or artificial motion cues. Among the key contributors is excessive optical flow-perceived visual motion that, when unmatched by vestibular input, leads to sensory conflict and discomfort. While previous efforts have explored geometric or hardware-based mitigation strategies, such methods often rely on predefined scene structures, manual tuning, or intrusive equipment. In this work, we propose U-MAD, a lightweight, real-time, AI-based solution that suppresses perceptually disruptive optical flow directly at the image level. Unlike prior handcrafted approaches, this method learns to attenuate high-intensity motion patterns from rendered frames without requiring mesh-level editing or scene-specific adaptation. Designed as a plug-and-play module, U-MAD integrates seamlessly into existing VR pipelines and generalizes well to procedurally generated environments. The experiments show that U-MAD consistently reduces average optical flow and enhances temporal stability across diverse scenes. A user study further supports the finding that reducing visual motion defects can improve perceptual comfort and alleviate cybersickness symptoms. These findings demonstrate that perceptually guided modulation of optical flow provides an effective and scalable approach to creating more user-friendly immersive experiences. The code will be released at https://github.com/XXXXX (upon publication).Keywords
Funding Information
- Guangzhou-HKUST(GZ) Joint Funding Scheme (2025A03J3955)
- AI Research and Learning Base of Urban Culture (2023WZJD008)
This publication has 58 references indexed in Scilit:
- Dynamic Cybersickness Mitigation via Adaptive FFR and FoV Adjustments2025
- Transcutaneous Auricular Vagus Nerve Stimulation for Visually Induced Motion Sickness: An eLORETA StudyBrain Topography, 2024
- High-fidelity Image Restoration of Large 3D Electron Microscopy VolumeMicroscopy and Microanalysis, 2024
- Frequency-Dependent Reduction of Cybersickness in Virtual Reality by Transcranial Oscillatory Stimulation of the Vestibular CortexNeurotherapeutics, 2023
- Cybersickness in current-generation virtual reality head-mounted displays: systematic review and outlookVirtual Reality, 2021
- Multisensory integration and the experience of scene instability, presence and cybersickness in virtual environmentsComputers in Human Behavior, 2020
- RAFT: Recurrent All-Pairs Field Transforms for Optical Flow2020
- Getting Rid of Cybersickness2020
- Optical flow approaches to the identification of brain dynamicsHuman Brain Mapping, 2009
- Predicting individual differences in motion sickness susceptibility by questionnairePersonality and Individual Differences, 2006