# TouchScale: 500 Hours of Human Vision and Touch for Visual-Tactile Learning

arXiv: https://arxiv.org/abs/2610.10288 · HTML: https://mlsanity.com/paper/2610.10288/

## Key facts

- No citing papers in the map yet (data through 7 Oct 2026).
- Builds on 15 of its 41 references that are in the map.
- First posted on arXiv 7 Oct 2026.

## Builds on (most cited first, 15 of 15)

- [EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos](https://mlsanity.com/paper/2507.12440/) (2025)
- [EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data](https://mlsanity.com/paper/2602.16710/) (2026)
- [Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper](https://mlsanity.com/paper/2507.15062/) (2025)
- [PressureVision: Estimating Hand Pressure from a Single RGB Image](https://mlsanity.com/paper/2203.10385/) (2022)
- [OPENTOUCH: Bringing Full-Hand Touch to Real-World Interaction](https://mlsanity.com/paper/2512.16842/) (2025)
- [T-Rex: Tactile-Reactive Dexterous Manipulation](https://mlsanity.com/paper/2606.17055/) (2026)
- [TouchAnything: A Dataset and Framework for Bimanual Tactile Estimation from Egocentric Video](https://mlsanity.com/paper/2605.13083/) (2026)
- [N0-VTLA: Scaling Vision-Tactile-Language-Action Model with Latent Tactile Tokens](https://mlsanity.com/paper/2607.23782/) (2026)
- [FEEL (Force-Enhanced Egocentric Learning): A Dataset for Physical Action Understanding](https://mlsanity.com/paper/2603.15847/) (2026)
- [HT-Bench: Benchmarking and Learning Dexterous Full-Hand Tactile Representations with Egocentric Vision](https://mlsanity.com/paper/2606.19161/) (2026)
- [Human-Centric Transferable Tactile Pre-Training for Dexterous Robotic Manipulation](https://mlsanity.com/paper/2607.01067/) (2026)
- [World In Your Hands: A Large-Scale and Open-Source Ecosystem for Learning Human-Centric Manipulation in the Wild](https://mlsanity.com/paper/2512.24310/) (2025)
- [EgoTL: Egocentric Think-Aloud Chains for Long-Horizon Tasks](https://mlsanity.com/paper/2604.09535/) (2026)
- [EgoTac: In-the-wild Tactile Prediction from Egocentric Vision](https://mlsanity.com/paper/2608.15060/) (2026)
- [TouchSight: Bare-Handed Tactile Prediction from Egocentric Video via Generative Visual Augmentation](https://mlsanity.com/paper/2609.20414/) (2026)

## Abstract (arXiv)

Large-scale egocentric human interaction data is becoming an important source of physical supervision for embodied learning, yet video alone leaves the contact and pressure that characterize physical interaction unrecorded. Recent visual-tactile datasets provide this missing supervision, but their synchronized tactile data remain far smaller in volume than human video. Moreover, the largest resources often merge recordings from different sensors or annotation procedures, which makes the effect of data scale difficult to isolate. We therefore introduce TouchScale, a 500-hour dataset of contact-rich human interaction recorded with a single unified wearable setup. Its approximately 2K predefined task descriptions span everyday activities and structured manipulation, and each recording temporally aligns egocentric RGB-D video with wrist RGB video and dense full-hand bimanual tactile measurements. Compared with prior tactile data, training on the full TouchScale raises zero-shot contact IoU on data from an unseen tactile sensor from 0.134 to 0.383. Pretraining a visual encoder on TouchScale also yields the highest action recognition accuracy on three benchmarks among the compared visual-tactile datasets. Used for visual-tactile mid-training of a robot policy, TouchScale improves the average real-world success rate across four contact-rich manipulation tasks from 22.5% to 57.5%. With the sensor and collection protocol held fixed, both zero-shot tactile prediction and robot success show an overall upward trend as more TouchScale data is used. These results suggest that human visual-tactile data collected at scale with consistent sensing benefits both perception and robot manipulation. We will publicly release TouchScale, including all synchronized visual-tactile recordings and reconstructed object models, to support future research on scalable visual-tactile learning.