English

TextToucher: Fine-Grained Text-to-Touch Generation

Computer Vision and Pattern Recognition 2025-01-10 v2

Abstract

Tactile sensation plays a crucial role in the development of multi-modal large models and embodied intelligence. To collect tactile data with minimal cost as possible, a series of studies have attempted to generate tactile images by vision-to-touch image translation. However, compared to text modality, visual modality-driven tactile generation cannot accurately depict human tactile sensation. In this work, we analyze the characteristics of tactile images in detail from two granularities: object-level (tactile texture, tactile shape), and sensor-level (gel status). We model these granularities of information through text descriptions and propose a fine-grained Text-to-Touch generation method (TextToucher) to generate high-quality tactile samples. Specifically, we introduce a multimodal large language model to build the text sentences about object-level tactile information and employ a set of learnable text prompts to represent the sensor-level tactile information. To better guide the tactile generation process with the built text information, we fuse the dual grains of text information and explore various dual-grain text conditioning methods within the diffusion transformer architecture. Furthermore, we propose a Contrastive Text-Touch Pre-training (CTTP) metric to precisely evaluate the quality of text-driven generated tactile data. Extensive experiments demonstrate the superiority of our TextToucher method. The source codes will be available at \url{https://github.com/TtuHamg/TextToucher}.

Keywords

Cite

@article{arxiv.2409.05427,
  title  = {TextToucher: Fine-Grained Text-to-Touch Generation},
  author = {Jiahang Tu and Hao Fu and Fengyu Yang and Hanbin Zhao and Chao Zhang and Hui Qian},
  journal= {arXiv preprint arXiv:2409.05427},
  year   = {2025}
}

Comments

This paper has been accepted by AAAI 2025

R2 v1 2026-06-28T18:38:14.781Z