FlowTouch: View-Invariant Visuo-Tactile Prediction

TL;DR

FlowTouch is a view-invariant model that predicts tactile information from visual data using 3D mesh encoding, enabling better generalization and application in manipulation tasks.

Contribution

It introduces a novel approach combining scene reconstruction and flow matching for view-invariant visuo-tactile prediction, addressing setup dependency issues.

Findings

Bridges the sim-to-real gap effectively.

Generalizes to new sensor instances.

Enables downstream grasp stability prediction.

Abstract

Tactile sensation is essential for contact-rich manipulation tasks. It provides direct feedback on object geometry, surface properties, and interaction forces, enhancing perception and enabling fine-grained control. An inherent limitation of tactile sensors is that readings are available only when an object is touched. This precludes their use during planning and the initial execution phase of a task. Predicting tactile information from visual information can bridge this gap. A common approach is to learn a direct mapping from camera images to the output of vision-based tactile sensors. However, the resulting model will depend strongly on the specific setup and on how well the camera can capture the area where an object is touched. In this work, we introduce FlowTouch, a novel model for view-invariant visuo-tactile prediction. Our key idea is to use an object's local 3D mesh to encode rich information for predicting tactile patterns while abstracting away from scene-dependent details. FlowTouch integrates scene reconstruction and Flow Matching-based models for image generation. Our results show that FlowTouch is able to bridge the sim-to-real gap and generalize to new sensor instances. We further show that the resulting tactile images can be used for downstream grasp stability prediction. Our code, datasets and videos are available at https://flowtouch.github.io/