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

cs.CV

Submitted: 2026-10-07

Updated: 2026-10-08

Comments: Project page: https://touch-scale.github.io/

Project page: https://touch-scale.github.io

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• FEEL (Force-Enhanced Egocentric Learning): A Dataset for Physical Action Understanding
• PressureVision: Estimating Hand Pressure from a Single RGB Image
• HT-Bench: Benchmarking and Learning Dexterous Full-Hand Tactile Representations with Egocentric Vision
• EgoTL: Egocentric Think-Aloud Chains for Long-Horizon Tasks
• $N_0$-VTLA: Scaling Vision-Tactile-Language-Action Model with Latent Tactile Tokens
• T-Rex: Tactile-Reactive Dexterous Manipulation
• OPENTOUCH: Bringing Full-Hand Touch to Real-World Interaction
• World In Your Hands: A Large-Scale and Open-Source Ecosystem for Learning Human-Centric Manipulation in the Wild
• EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos
• Human-Centric Transferable Tactile Pre-Training for Dexterous Robotic Manipulation
• EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data
• TouchSight: Bare-Handed Tactile Prediction from Egocentric Video via Generative Visual Augmentation
• TouchAnything: A Dataset and Framework for Bimanual Tactile Estimation from Egocentric Video
• Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models