Flow-Aware Diffusion for Real-Time VR Restoration: Enhancing Spatiotemporal Coherence and Efficiency
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915760915349504 |
|---|---|
| author | Zhu, Yitong Dong, Qianghong Jiang, Guanxuan Liang, Zhuowen Wang, Yuyang |
| author_facet | Zhu, Yitong Dong, Qianghong Jiang, Guanxuan Liang, Zhuowen Wang, Yuyang |
| contents | 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 confirms that reducing visual motion leads to improved perceptual comfort and alleviated 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). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_18786 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Flow-Aware Diffusion for Real-Time VR Restoration: Enhancing Spatiotemporal Coherence and Efficiency Zhu, Yitong Dong, Qianghong Jiang, Guanxuan Liang, Zhuowen Wang, Yuyang Human-Computer Interaction 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 confirms that reducing visual motion leads to improved perceptual comfort and alleviated 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). |
| title | Flow-Aware Diffusion for Real-Time VR Restoration: Enhancing Spatiotemporal Coherence and Efficiency |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2506.18786 |