# TouchSight: Bare-Handed Tactile Prediction from Egocentric Video via Generative Visual Augmentation

arXiv: https://arxiv.org/abs/2609.20414 · HTML: https://mlsanity.com/paper/2609.20414/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 45 references that are in the map.
- First posted on arXiv 17 Sep 2026.

## Builds on (most cited first, 30 of 34)

- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction](https://mlsanity.com/paper/2203.01577/) (2022)
- [ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation](https://mlsanity.com/paper/2204.13662/) (2022)
- [Reconstructing Hands in 3D with Transformers](https://mlsanity.com/paper/2312.05251/) (2023)
- [H2O: Two Hands Manipulating Objects for First Person Interaction Recognition](https://mlsanity.com/paper/2104.11181/) (2021)
- [EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video](https://mlsanity.com/paper/2505.11709/) (2025)
- [Capturing and Inferring Dense Full-Body Human-Scene Contact](https://mlsanity.com/paper/2206.09553/) (2022)
- [DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulation](https://mlsanity.com/paper/2005.14679/) (2020)
- [Seedance 2.0: Advancing Video Generation for World Complexity](https://mlsanity.com/paper/2604.14148/) (2026)
- [ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imaging](https://mlsanity.com/paper/1904.06830/) (2019)
- [HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos](https://mlsanity.com/paper/2411.19167/) (2024)
- [Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation](https://mlsanity.com/paper/2503.02881/) (2025)
- [TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding](https://mlsanity.com/paper/2401.08399/) (2024)
- [OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion](https://mlsanity.com/paper/2403.19417/) (2024)
- [Connecting Touch and Vision via Cross-Modal Prediction](https://mlsanity.com/paper/1906.06322/) (2019)
- [Sparsh: Self-supervised touch representations for vision-based tactile sensing](https://mlsanity.com/paper/2410.24090/) (2024)
- [DECO: Dense Estimation of 3D Human-Scene Contact In The Wild](https://mlsanity.com/paper/2309.15273/) (2023)
- [Transferable Tactile Transformers for Representation Learning Across Diverse Sensors and Tasks](https://mlsanity.com/paper/2406.13640/) (2024)
- [PressureVision: Estimating Hand Pressure from a Single RGB Image](https://mlsanity.com/paper/2203.10385/) (2022)
- [ViTaMIn: Learning Contact-Rich Tasks Through Robot-Free Visuo-Tactile Manipulation Interface](https://mlsanity.com/paper/2504.06156/) (2025)
- [EgoPressure: A Dataset for Hand Pressure and Pose Estimation in Egocentric Vision](https://mlsanity.com/paper/2409.02224/) (2024)
- [VITaL Pretraining: Visuo-Tactile Pretraining for Tactile and Non-Tactile Manipulation Policies](https://mlsanity.com/paper/2403.11898/) (2024)
- [OPENTOUCH: Bringing Full-Hand Touch to Real-World Interaction](https://mlsanity.com/paper/2512.16842/) (2025)
- [Learning Dense Hand Contact Estimation from Imbalanced Data](https://mlsanity.com/paper/2505.11152/) (2025)
- [PressureVision++: Estimating Fingertip Pressure from Diverse RGB Images](https://mlsanity.com/paper/2301.02310/) (2023)

## Built on by (most cited first, 1 of 1)

- [TouchScale: 500 Hours of Human Vision and Touch for Visual-Tactile Learning](https://mlsanity.com/paper/2610.10288/) (2026)

## Abstract (arXiv)

Tactile signals provide direct contact and force measurements that are essential for understanding physical interactions and enabling dexterous robotic manipulation. However, tactile sensing requires direct measurement at contact interfaces, making large-scale data collection reliant on intrusive, costly, and restrictive instrumentation. We present TouchSight, a monocular egocentric vision framework for dense full-hand contact force prediction that leverages 500 hours of pressure-glove recordings and extensive hand-object interaction (HOI) data. To address the appearance gap between gloved training data and bare-hand real-world scenarios, we construct TwinTouch-20H: 20 hours of paired visual data in which generative video models re-render gloved recordings as bare-hand observations against new backgrounds while preserving the original measured tactile labels. TouchSight predicts dense force from both gloved and generated bare-hand videos, outperforms prior contact prediction methods on OakInk2, qualitatively generalizes to natural bare-hand egocentric videos from unseen datasets, and improves consistently as glove supervision scales. These results demonstrate that dense tactile signals can be recovered from egocentric vision alone, without tactile instrumentation at capture time.