# Tac-DINO: Learning Vision-Tactile Features with Patch Alignment

arXiv: https://arxiv.org/abs/2606.12069 · HTML: https://mlsanity.com/paper/2606.12069/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 55 of its 68 references that are in the map.
- First posted on arXiv 10 Jun 2026.

## Builds on (most cited first, 30 of 55)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [Objaverse-XL: A Universe of 10M+ 3D Objects](https://mlsanity.com/paper/2307.05663/) (2023)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [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)
- [Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation](https://mlsanity.com/paper/2503.02881/) (2025)
- [Binding Touch to Everything: Learning Unified Multimodal Tactile Representations](https://mlsanity.com/paper/2401.18084/) (2024)
- [Touch and Go: Learning from Human-Collected Vision and Touch](https://mlsanity.com/paper/2211.12498/) (2022)
- [ObjectFolder 2.0: A Multisensory Object Dataset for Sim2Real Transfer](https://mlsanity.com/paper/2204.02389/) (2022)
- [3D-ViTac: Learning Fine-Grained Manipulation with Visuo-Tactile Sensing](https://mlsanity.com/paper/2410.24091/) (2024)
- [ObjectFolder: A Dataset of Objects with Implicit Visual, Auditory, and Tactile Representations](https://mlsanity.com/paper/2109.07991/) (2021)
- [The Feeling of Success: Does Touch Sensing Help Predict Grasp Outcomes?](https://mlsanity.com/paper/1710.05512/) (2017)
- [Dexterity from Touch: Self-Supervised Pre-Training of Tactile Representations with Robotic Play](https://mlsanity.com/paper/2303.12076/) (2023)
- [Robot Synesthesia: In-Hand Manipulation with Visuotactile Sensing](https://mlsanity.com/paper/2312.01853/) (2023)
- [AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors](https://mlsanity.com/paper/2502.12191/) (2025)
- [GelSlim3.0: High-Resolution Measurement of Shape, Force and Slip in a Compact Tactile-Sensing Finger](https://mlsanity.com/paper/2103.12269/) (2021)
- [The ObjectFolder Benchmark: Multisensory Learning with Neural and Real Objects](https://mlsanity.com/paper/2306.00956/) (2023)
- [A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Models](https://mlsanity.com/paper/2502.13187/) (2025)
- [ViTacFormer: Learning Cross-Modal Representation for Visuo-Tactile Dexterous Manipulation](https://mlsanity.com/paper/2506.15953/) (2025)
- [Vision in Action: Learning Active Perception from Human Demonstrations](https://mlsanity.com/paper/2506.15666/) (2025)
- [See, Hear, and Read: Deep Aligned Representations](https://mlsanity.com/paper/1706.00932/) (2017)
- [Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper](https://mlsanity.com/paper/2507.15062/) (2025)
- [Visuo-Tactile World Models](https://mlsanity.com/paper/2602.06001/) (2026)

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

- [Self-Supervised Anchoring of Fingertip Sensing to Proprioception and Proactive Actions for Robot Imitation Learning](https://mlsanity.com/paper/2609.29822/) (2026)

## Abstract (arXiv)

Touch is the primary medium through which humans interact with the environment. Currently, tactile learning mainly focuses on image-level pretraining or alignment. However, tactile signals correspond to local object contact, while research into scale alignment and holographic matching remains limited and proper datasets and benchmarks also lack. To bridge this gap, we first construct a data collection system to acquire a large-scale tactile dataset, with over 20 K tactile contacts from 505 real-world objects. Building on this dataset, we design a Vis-Tac Holographic Matching Benchmark to evaluate vision-tactile local-to-global alignment ability. Then we propose Vision-Tactile Patch Alignment (VTPA) methods for vision-tactile representation learning. Experiments demonstrate that these exceed the performance of methods without alignment and align with whole-object images.