Search papers, labs, and topics across Lattice.
This paper introduces VQ-Touch, a novel tactile generation framework that synthesizes high-fidelity tactile data to minimize reliance on costly sensors in robotic perception and human-machine interaction. By employing a discrete diffusion decoder and the DM-VQGAN representation learner, VQ-Touch efficiently captures complex deformation and texture features, enhancing generalization across diverse sensors and scenarios. Experimental results demonstrate that VQ-Touch outperforms existing methods in various tasks, highlighting its potential for broader applications in tactile information acquisition.
VQ-Touch achieves superior tactile data generation while drastically reducing the need for expensive sensors, reshaping the landscape of robotic perception.
Tactile image generation significantly reduces the dependency on expensive and wear-prone sensors by synthesizing high-fidelity tactile data, offering an efficient solution for tactile information acquisition in robotic perception and human-machine interaction systems. However, existing methods depend on large-scale, diverse datasets from specific sensors and lack efficient data utilization and robust generalization capabilities, struggling in vision-limited environments. To address this, we introduce VQ-Touch, a tactile generation framework that supports both cross-sensor and multi-scenario applications. Specifically, to efficiently extract complex deformation and texture features from the data, we propose DM-VQGAN, an effective tactile representation learner. Furthermore, we introduce a discrete diffusion decoder with a unified conditioning interface, supporting multimodal generation tasks such as images and labels, and enhances the model's generalization capability through few-shot mixed training, thus achieving compatibility with current mainstream sensors and their variants. Experiments show that VQ-Touch surpasses state-of-the-art methods in multiple tasks.
