GAN-Based Fine-Tuning of Vibrotactile Signals to Render Material Surfaces
The design productivity of fine-tuning for vibrotactile stimuli becomes important as consumer devices equipped with vibrotactile actuators will become wide-spread. The fine-tuned vibrotactile stimuli output by vibrotactile actuators allows the end-users to feel the surface of the virtual material. H...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8963970/ |
| Summary: | The design productivity of fine-tuning for vibrotactile stimuli becomes important as consumer devices equipped with vibrotactile actuators will become wide-spread. The fine-tuned vibrotactile stimuli output by vibrotactile actuators allows the end-users to feel the surface of the virtual material. However, there is no suitable tool for fine-tuning while there are existing tools suitable for initial designing. In this paper, we test whether we can use GAN (Generative Adversarial Network)-based vibrotactile signal generator at the tuning phase. The generator provides a material-level interface to designers. Designers can define any intermediate materials among pre-defined 108 materials and obtain corresponding intermediate signals that the generator generates. We showed the applicability of the generator to the fine-tuning of vibrotactile signals from the viewpoints of principal component analysis and a user test. |
|---|---|
| ISSN: | 2169-3536 |