Live Demonstration: NeuroTouch - A Neuromorphic Vision-Based Tactile Sensor for Real-Time Gesture Recognition

Abstract

We propose to demonstrate NeuroTouch, a vision-based tactile sensor that combines a highly deformable dome-shaped soft material with an integrated neuromorphic camera, leveraging frame-based and event-based vision for multi-finger gesture detection. Our approach transforms an elastic body into a rich and nuanced interactive controller by tracking markers printed on its surface with event-based methods and classifying the displacement field into one of five gesture types with a corresponding intensity. We will demonstrate this novel control interface with a simple video game, highlighting the potential of soft controllers for entertainment applications.

Cite

Text

Hoffmann et al. "Live Demonstration: NeuroTouch - A Neuromorphic Vision-Based Tactile Sensor for Real-Time Gesture Recognition." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025.

Markdown

[Hoffmann et al. "Live Demonstration: NeuroTouch - A Neuromorphic Vision-Based Tactile Sensor for Real-Time Gesture Recognition." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025.](https://mlanthology.org/cvprw/2025/hoffmann2025cvprw-live/)

BibTeX

@inproceedings{hoffmann2025cvprw-live,
  title     = {{Live Demonstration: NeuroTouch - A Neuromorphic Vision-Based Tactile Sensor for Real-Time Gesture Recognition}},
  author    = {Hoffmann, Victor and Cavinato, Valentina and Scheper, Kirk Y. W.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2025},
  pages     = {5023-5024},
  url       = {https://mlanthology.org/cvprw/2025/hoffmann2025cvprw-live/}
}