HaptoFlow: High-Fidelity Real-Time Vibrotactile Generation via Flow Matching for Virtual Reality

2026-08-03

AI Summary

This work addresses the scalability challenge in virtual reality haptic feedback, where achieving both expressive waveform fidelity and real-time performance across diverse interaction conditions remains difficult. To this end, we introduce flow matching—a technique previously unexplored in haptics—to propose a conditional vibrotactile waveform generation model. The model leverages interaction parameters such as material type, stroking velocity, and applied force to learn a continuous vector field that transports samples from a base distribution to target haptic waveforms, enabling high-fidelity, low-latency rendering. Experimental results demonstrate that our approach outperforms existing baselines in both waveform reconstruction accuracy and inference efficiency, achieving system latency below the visuo-haptic perception threshold. Furthermore, it significantly enhances perceived tactile quality across a range of materials, effectively overcoming the longstanding trade-off between expressiveness and responsiveness in generative haptic models.

Abstract

Haptic feedback is widely employed to enhance immersion in Virtual Reality (VR) environments. However, designing haptic stimuli that cover diverse interaction conditions remains a significant scalability challenge. Data-driven haptic generation has emerged as a promising approach, yet existing models face an inherent trade-off between waveform expressiveness and inference responsiveness, which becomes increasingly critical as training data grow in scale and diversity. To address this challenge, we propose HaptoFlow, a vibrotactile generative model based on Flow Matching, designed for interactive real-time haptic rendering in VR. Flow Matching learns a continuous vector field that transforms a base distribution into the target data distribution, enabling efficient representation of complex haptic data distributions and thereby facilitating both high-quality generation and computational efficiency. We train HaptoFlow conditioned on material labels and interaction parameters (stroking velocity and applied force), and integrate it into a VR system. Technical evaluation demonstrates that HaptoFlow outperforms all baseline methods in both waveform reproduction accuracy and inference latency. Furthermore, user studies confirm that the system latency falls well within the perceptual threshold of visual-haptic delay, and statistically significant improvements in perceived haptic quality are observed for a subset of materials. These findings establish a practical foundation for scalable, data-driven haptic content creation in VR, and provide latency benchmarks that inform the design of future real-time haptic rendering systems. Project page: https://tamago117.github.io/HaptoFlow/.

Problem

• haptic feedback
• real-time rendering
• data-driven generation
• scalability
• virtual reality

Innovation

• Flow Matching
• Vibrotactile Generation
• Real-Time Haptic Rendering
• Virtual Reality
• Data-Driven Haptics