N-euro Predictor: A Neural Network Approach for Smoothing and Predicting Motion Trajectory

Qijia Shao,Jian Wang, Bing Zhou, Vu An Tran, Gurunandan Krishnan,Shree Nayar

Ubicomp 2023(2023)

引用 0|浏览6
暂无评分
摘要
Jitter and lag severely impact the smoothness and responsiveness of user experience on vision-based human-display interactive systems such as phones, TVs, and VR/AR. Current manually-tuned filters for smoothing and predicting motion trajectory struggle to effectively address both issues, especially for applications that have a large range of movement speed. To overcome this, we introduce N-euro, a residual-learning-based neural network predictor that can simultaneously reduce jitter and lag while maintaining low computational overhead. Compared to the fine-tuned existing filters, N-euro improves prediction performance by 36% and smoothing performance by 42%. We fabricated a Fish Tank VR system and an AR mirror system and conducted a user experience study (n=34) with the real-time implementation of N-euro. Our results indicate that the N-euro predictor brings a statistically significant improvement in user experience. With its validated effectiveness and usability, we expect this approach to bring a better user experience to various vision-based interactive systems.
更多
查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络