|
Persistent Identifier
|
doi:10.60507/FK2/QODWTV |
|
Publication Date
|
2026-05-26 |
|
Title
| Hoi!-A Multimodal Dataset for Force-Grounded, Cross-View Articulated Manipulation |
|
Alternative URL
| "https://timengelbracht.github.io/Hoi-Dataset-Website/" |
|
Author
| Engelbracht, Tim (ETH Zürich) - ORCID: https://orcid.org/0009-0009-4853-5526
Zurbrügg, René (ETH Zürich) - ORCID: https://orcid.org/0000-0003-2773-9369
Wohlrapp, Matteo (ETH Zürich)
Büchner, Martin (University of Freiburg) - ORCID: https://orcid.org/0000-0001-8725-1213
Valada, Abhinav (University of Freiburg) - ORCID: https://orcid.org/0000-0003-4710-3114
Pollefeys, Marc (ETH Zürich) - ORCID: https://orcid.org/0000-0003-2448-2318
Blum, Hermann (University of Bonn & Lamarr Institute) - ORCID: https://orcid.org/0000-0002-1713-7877
Bauer, Zuria (ETH Zürich) - ORCID: https://orcid.org/0000-0001-8447-2344 |
|
Contact
|
Use email button above to contact.
Engelbracht, Tim (ETH Zürich)
Blum, Hermann (University of Bonn & Lamarr Institute)
Bauer, Zuria (ETH Zürich) |
|
Description
| We present a dataset for force-grounded, cross-view articulated manipulation that couples what is seen with what is done and what is felt during real human interaction. The dataset contains 3048 sequences across 381 articulated objects in 38 environments. Each object is operated under four embodiments - (i) human hand, (ii) human hand with a wrist-mounted camera, (iii) handheld UMI gripper, and (iv) a custom Hoi! gripper - where the tool embodiment provides synchronized end-effector forces and tactile sensing. Our dataset offers a holistic view of interaction understanding from video, enabling researchers to evaluate how well methods transfer between human and robotic viewpoints, but also investigate underexplored modalities such as force sensing and prediction. Further information can be found on the Website. (2026-03-20) |
|
Subject
| Computer and Information Science; Engineering |
|
Subject Refinement
| vision |
|
FreeKeyword
| articulation
force sensing
robotic manipulation
egocentric vision |
|
Related Publication
| IsSupplementTo: Engelbracht, T., Zurbrügg, R., Wohlrapp, M., Büchner, M., Valada, A., Pollefeys, M., ... & Bauer, Z. (2025). Hoi!--A Multimodal Dataset for Force-Grounded, Cross-View Articulated Manipulation. CVPR 2026
IsSupplementTo: Engelbracht, T., Zurbrügg, R., Wohlrapp, M., Büchner, M., Valada, A., Pollefeys, M., ... & Bauer, Z. (2025). Hoi!--A Multimodal Dataset for Force-Grounded, Cross-View Articulated Manipulation. CVPR 2026 arXiv 2512.04884 https://doi.org/10.48550/arXiv.2512.04884 |
|
Notes
| version 0.1 |
|
Grant Information
| ETH Career Seed
Robotics Insitute Germany |
|
Depositor
| Blum, Hermann |
|
Deposit Date
| 2026-03-20 |