Seeing My Future: Predicting Situated Interaction Behavior in Virtual Reality

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xu, Yuan, Zhang, Zimu, Ma, Xiaoxuan, Zhu, Wentao, Qiao, Yu, Wang, Yizhou
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911206443319296
author Xu, Yuan
Zhang, Zimu
Ma, Xiaoxuan
Zhu, Wentao
Qiao, Yu
Wang, Yizhou
author_facet Xu, Yuan
Zhang, Zimu
Ma, Xiaoxuan
Zhu, Wentao
Qiao, Yu
Wang, Yizhou
contents Virtual and augmented reality systems increasingly demand intelligent adaptation to user behaviors for enhanced interaction experiences. Achieving this requires accurately understanding human intentions and predicting future situated behaviors - such as gaze direction and object interactions - which is vital for creating responsive VR/AR environments and applications like personalized assistants. However, accurate behavioral prediction demands modeling the underlying cognitive processes that drive human-environment interactions. In this work, we introduce a hierarchical, intention-aware framework that models human intentions and predicts detailed situated behaviors by leveraging cognitive mechanisms. Given historical human dynamics and the observation of scene contexts, our framework first identifies potential interaction targets and forecasts fine-grained future behaviors. We propose a dynamic Graph Convolutional Network (GCN) to effectively capture human-environment relationships. Extensive experiments on challenging real-world benchmarks and live VR environment demonstrate the effectiveness of our approach, achieving superior performance across all metrics and enabling practical applications for proactive VR systems that anticipate user behaviors and adapt virtual environments accordingly.
format Preprint
id arxiv_https___arxiv_org_abs_2510_10742
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Seeing My Future: Predicting Situated Interaction Behavior in Virtual Reality
Xu, Yuan
Zhang, Zimu
Ma, Xiaoxuan
Zhu, Wentao
Qiao, Yu
Wang, Yizhou
Computer Vision and Pattern Recognition
Machine Learning
Virtual and augmented reality systems increasingly demand intelligent adaptation to user behaviors for enhanced interaction experiences. Achieving this requires accurately understanding human intentions and predicting future situated behaviors - such as gaze direction and object interactions - which is vital for creating responsive VR/AR environments and applications like personalized assistants. However, accurate behavioral prediction demands modeling the underlying cognitive processes that drive human-environment interactions. In this work, we introduce a hierarchical, intention-aware framework that models human intentions and predicts detailed situated behaviors by leveraging cognitive mechanisms. Given historical human dynamics and the observation of scene contexts, our framework first identifies potential interaction targets and forecasts fine-grained future behaviors. We propose a dynamic Graph Convolutional Network (GCN) to effectively capture human-environment relationships. Extensive experiments on challenging real-world benchmarks and live VR environment demonstrate the effectiveness of our approach, achieving superior performance across all metrics and enabling practical applications for proactive VR systems that anticipate user behaviors and adapt virtual environments accordingly.
title Seeing My Future: Predicting Situated Interaction Behavior in Virtual Reality
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2510.10742