# BiView-Touch: Learning Bimanual Tactile Representations by Cross-Hand Completion

arXiv: https://arxiv.org/abs/2609.23352 · HTML: https://mlsanity.com/paper/2609.23352/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 49 references that are in the map.
- First posted on arXiv 20 Sep 2026.

## Builds on (most cited first, 17 of 17)

- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion](https://mlsanity.com/paper/2210.10716/) (2022)
- [3D-ViTac: Learning Fine-Grained Manipulation with Visuo-Tactile Sensing](https://mlsanity.com/paper/2410.24091/) (2024)
- [AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors](https://mlsanity.com/paper/2502.12191/) (2025)
- [Improved GelSight Tactile Sensor for Measuring Geometry and Slip](https://mlsanity.com/paper/1708.00922/) (2017)
- [Bi-Touch: Bimanual Tactile Manipulation with Sim-to-Real Deep Reinforcement Learning](https://mlsanity.com/paper/2307.06423/) (2023)
- [VITaL Pretraining: Visuo-Tactile Pretraining for Tactile and Non-Tactile Manipulation Policies](https://mlsanity.com/paper/2403.11898/) (2024)
- [exUMI: Extensible Robot Teaching System with Action-aware Task-agnostic Tactile Representation](https://mlsanity.com/paper/2509.14688/) (2025)
- [Canonical Representation and Force-Based Pretraining of 3D Tactile for Dexterous Visuo-Tactile Policy Learning](https://mlsanity.com/paper/2409.17549/) (2024)
- [Dynamic Modeling of Hand-Object Interactions via Tactile Sensing](https://mlsanity.com/paper/2109.04378/) (2021)
- [Learn from Incomplete Tactile Data: Tactile Representation Learning with Masked Autoencoders](https://mlsanity.com/paper/2307.07358/) (2023)
- [TouchAnything: A Dataset and Framework for Bimanual Tactile Estimation from Egocentric Video](https://mlsanity.com/paper/2605.13083/) (2026)
- [VTAO-BiManip: Masked Visual-Tactile-Action Pre-training with Object Understanding for Bimanual Dexterous Manipulation](https://mlsanity.com/paper/2501.03606/) (2025)
- [Blind Dexterous Grasping via Real2Sim2Real Tactile Policy Learning](https://mlsanity.com/paper/2606.11767/) (2026)
- [STAR: Sparse Tactile Representation Learning in Vision-Tactile-Language-Action Models for Dexterous Manipulation](https://mlsanity.com/paper/2609.12549/) (2026)

## Abstract (arXiv)

Bimanual interaction produces complementary tactile views of the same physical process, yet existing tactile representation learning largely models the two hands independently or combines them only for downstream prediction, leaving their cross-hand relationship unexplored. To exploit this overlooked structure, we introduce BiView-Touch, a tactile-only framework that completes masked target-hand latents from the remaining visible target-hand regions and the synchronized full contralateral hand. A student encoder with a geometry-conditioned directional decoder predicts full-view EMA latent targets, while temporal and layout counterfactuals encourage sensitivity to synchronized and anatomically organized source information. Controlled ablations and source-context interventions show that BiView-Touch learns structured cross-hand dependence on temporally aligned and anatomically organized contralateral tactile context, rather than benefiting from bilateral input alone. On the public HumanTouch dataset, its frozen representations consistently outperform representative self-supervised baselines across low-label settings. With only 5% downstream labels, BiView-Touch achieves relative balanced-accuracy gains of 7.1% on bilateral wrist-motion recognition and 14.1% on force-derived interaction-phase recognition. We further introduce BVT-20, a 20-task bilateral tactile dataset, and demonstrate transfer across recording sessions and pretraining corpora, including transfer to a held-out bimanual task. Our code and dataset details are available on the anonymous project page: https://anonymous.4open.science/w/biview-touch-review-site-050C/.