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

Hugging Face Daily Papers Papers
tactile-sensing embodied-ai robotics dataset multimodal-learning egocentric-video pretraining

Summary

TouchScale 引入了一个 500 小时的人类视觉-触觉交互数据集，使用统一的可穿戴设备同步采集 egocentric RGB-D 视频、手腕视频与全手双触觉测量，用于视觉-触觉预训练和机器人操作策略学习，在零样本触觉预测和真实机器人操作成功率上均取得显著提升。

Large-scale egocentric human interaction data is becoming an important source of physical supervision for embodied learning, yet video alone leaves the contact and pressure that characterize physical interaction unrecorded. Recent visual-tactile datasets provide this missing supervision, but their synchronized tactile data remain far smaller in volume than human video. Moreover, the largest resources often merge recordings from different sensors or annotation procedures, which makes the effect of data scale difficult to isolate. We therefore introduce TouchScale, a 500-hour dataset of contact-rich human interaction recorded with a single unified wearable setup. Its approximately 2K predefined task descriptions span everyday activities and structured manipulation, and each recording temporally aligns egocentric RGB-D video with wrist RGB video and dense full-hand bimanual tactile measurements. Compared with prior tactile data, training on the full TouchScale raises zero-shot contact IoU on data from an unseen tactile sensor from 0.134 to 0.383. Pretraining a visual encoder on TouchScale also yields the highest action recognition accuracy on three benchmarks among the compared visual-tactile datasets. Used for visual-tactile mid-training of a robot policy, TouchScale improves the average real-world success rate across four contact-rich manipulation tasks from 22.5% to 57.5%. With the sensor and collection protocol held fixed, both zero-shot tactile prediction and robot success show an overall upward trend as more TouchScale data is used. These results suggest that human visual-tactile data collected at scale with consistent sensing benefits both perception and robot manipulation. We will publicly release TouchScale, including all synchronized visual-tactile recordings and reconstructed object models, to support future research on scalable visual-tactile learning.
Original Article
View Cached Full Text

Cached at: 10/12/26, 06:53 AM

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

Source: https://huggingface.co/papers/2610.10288 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Large-scaleegocentrichumaninteractiondataisbecominganimportantsourceofphysicalsupervisionforembodiedlearning,yetvideoaloneleavesthecontactandpressurethatcharacterizephysicalinteractionunrecorded.Recentvisual-tactiledatasetsprovidethismissingsupervision,buttheirsynchronizedtactiledataremainfarsmallerinvolumethanhumanvideo.Moreover,thelargestresourcesoftenmergerecordingsfromdifferentsensorsorannotationprocedures,whichmakestheeffectofdatascaledifficulttoisolate.WethereforeintroduceTouchScale,a500-hourdatasetofcontact-richhumaninteractionrecordedwithasingleunifiedwearablesetup.Itsapproximately2Kpredefinedtaskdescriptionsspaneverydayactivitiesandstructuredmanipulation,andeachrecordingtemporallyalignsegocentricRGB-DvideowithwristRGBvideoanddensefull-handbimanualtactilemeasurements.Comparedwithpriortactiledata,trainingonthefullTouchScaleraiseszero-shotcontactIoUondatafromanunseentactilesensorfrom0.134to0.383.PretrainingavisualencoderonTouchScalealsoyieldsthehighestactionrecognitionaccuracyonthreebenchmarksamongthecomparedvisual-tactiledatasets.Usedforvisual-tactilemid-trainingofarobotpolicy,TouchScaleimprovestheaveragereal-worldsuccessrateacrossfourcontact-richmanipulationtasksfrom22.5%to57.5%.Withthesensorandcollectionprotocolheldfixed,bothzero-shottactilepredictionandrobotsuccessshowanoverallupwardtrendasmoreTouchScaledataisused.Theseresultssuggestthathumanvisual-tactiledatacollectedatscalewithconsistentsensingbenefitsbothperceptionandrobotmanipulation.WewillpubliclyreleaseTouchScale,includingallsynchronizedvisual-tactilerecordingsandreconstructedobjectmodels,tosupportfutureresearchonscalablevisual-tactilelearning.

View arXiv pageView PDFProject pageGitHubAdd to collection

Get this paper in your agent:

hf papers read 2610\.10288

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.10288 in a model README.md to link it from this page.

Datasets citing this paper1

#### 2077AIDataFoundation/TouchScale Viewer• Updated3 days ago • 15.3k • 2.57k • 5

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.10288 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

EyeRobot 2.0: Active Gaze for Precise Manipulation without Wrist Cameras

Hugging Face Daily Papers

EyeRobot 2.0 介绍了一种受人类视觉启发的机器人操作框架，通过双目相机上的主动注视（Active Visual Fixation）实现精细双臂操作，无需腕部相机。研究在真实与模拟任务中进行了上千次试验，证明该方法在物体遮挡腕部相机时可将成功率提升至对手的两倍以上。

HumanNet: Scaling Human-centric Video Learning to One Million Hours

Hugging Face Daily Papers

HumanNet is a large-scale human-centric video dataset with one million hours of annotated footage, designed to train vision-language-action models. It demonstrates that egocentric human video can effectively replace robot data for embodied intelligence tasks.