# DenseTact 2.0: Optical Tactile Sensor for Shape and Force Reconstruction

arXiv: https://arxiv.org/abs/2209.10122 · HTML: https://mlsanity.com/paper/2209.10122/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Sep 2022.

## Built on by (most cited first, 9 of 9)

- [VLA-Touch: Enhancing Vision-Language-Action Models with Dual-Level Tactile Feedback](https://mlsanity.com/paper/2507.17294/) (2025)
- [Touch-GS: Visual-Tactile Supervised 3D Gaussian Splatting](https://mlsanity.com/paper/2403.09875/) (2024)
- [X-Capture: An Open-Source Portable Device for Multi-Sensory Learning](https://mlsanity.com/paper/2504.02318/) (2025)
- [DexSkin: High-Coverage Conformable Robotic Skin for Learning Contact-Rich Manipulation](https://mlsanity.com/paper/2509.18830/) (2025)
- [NLiPsCalib: An Efficient Calibration Framework for High-Fidelity 3D Reconstruction of Curved Visuotactile Sensors](https://mlsanity.com/paper/2603.09319/) (2026)
- [Enhance Vision-based Tactile Sensors via Dynamic Illumination and Image Fusion](https://mlsanity.com/paper/2504.00017/) (2025)
- [The Role of Tactile Sensing for Learning Reach and Grasp](https://mlsanity.com/paper/2502.20367/) (2025)
- [Fluidically Innervated Lattices Make Versatile and Durable Tactile Sensors](https://mlsanity.com/paper/2507.21225/) (2025)
- [DOT-Sim: Differentiable Optical Tactile Simulation with Precise Real-to-Sim Physical Calibration](https://mlsanity.com/paper/2604.27367/) (2026)

## Abstract (arXiv)

Collaborative robots stand to have an immense impact on both human welfare in domestic service applications and industrial superiority in advanced manufacturing with dexterous assembly. The outstanding challenge is providing robotic fingertips with a physical design that makes them adept at performing dexterous tasks that require high-resolution, calibrated shape reconstruction and force sensing. In this work, we present DenseTact 2.0, an optical-tactile sensor capable of visualizing the deformed surface of a soft fingertip and using that image in a neural network to perform both calibrated shape reconstruction and 6-axis wrench estimation. We demonstrate the sensor accuracy of 0.3633mm per pixel for shape reconstruction, 0.410N for forces, 0.387Nmm for torques, and the ability to calibrate new fingers through transfer learning, which achieves comparable performance with only 12% of the non-transfer learning dataset size.