# Teaching Cameras to Feel: Estimating Tactile Physical Properties of Surfaces From Images

arXiv: https://arxiv.org/abs/2004.14487 · HTML: https://mlsanity.com/paper/2004.14487/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Apr 2020.

## Built on by (most cited first, 3 of 3)

- [Visual-Tactile Cross-Modal Data Generation using Residue-Fusion GAN with Feature-Matching and Perceptual Losses](https://mlsanity.com/paper/2107.05468/) (2021)
- [Interactive Learning of Physical Object Properties Through Robot Manipulation and Database of Object Measurements](https://mlsanity.com/paper/2404.07344/) (2024)
- [Beyond Thermal Imaging: Inferring Thermophysical Properties from Time-Resolved Thermal Observations](https://mlsanity.com/paper/2607.07962/) (2026)

## Abstract (arXiv)

The connection between visual input and tactile sensing is critical for object manipulation tasks such as grasping and pushing. In this work, we introduce the challenging task of estimating a set of tactile physical properties from visual information. We aim to build a model that learns the complex mapping between visual information and tactile physical properties. We construct a first of its kind image-tactile dataset with over 400 multiview image sequences and the corresponding tactile properties. A total of fifteen tactile physical properties across categories including friction, compliance, adhesion, texture, and thermal conductance are measured and then estimated by our models. We develop a cross-modal framework comprised of an adversarial objective and a novel visuo-tactile joint classification loss. Additionally, we develop a neural architecture search framework capable of selecting optimal combinations of viewing angles for estimating a given physical property.