Metraipolis › archive › dc_7feaccd203f0
TouchScale: 500 Hours of Human Vision and Touch for Visual-Tactile Learning — arXiv:2610.10288
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.10288
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:47:59.498Z
- SHA-256 of the archived text
c2e79e44eafd429f22c12bb5ebc1305f823744c4e4cfac978b2d94e6b7eeff53- Stable URL of this page
https://metraipolis.com/documento/dc_7feaccd203f0
How to cite
TouchScale: 500 Hours of Human Vision and Touch for Visual-Tactile Learning — arXiv:2610.10288 — arXiv (en), https://arxiv.org/abs/2610.10288 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7feaccd203f0 (Metraipolis archive dc_7feaccd203f0, sha256 c2e79e44eafd429f22c12bb5ebc1305f823744c4e4cfac978b2d94e6b7eeff53)
BibTeX
@misc{dc7feaccd203f0,
title = {TouchScale: 500 Hours of Human Vision and Touch for Visual-Tactile Learning — arXiv:2610.10288},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.10288},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7feaccd203f0; sha256 c2e79e44eafd429f22c12bb5ebc1305f823744c4e4cfac978b2d94e6b7eeff53},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10288. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.10288 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T12:18:15.473Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).