Reconstructing Three-Dimensional Models of Interacting Humans
(2025) In IEEE Transactions on Pattern Analysis and Machine Intelligence 47(12). p.10870-10881- Abstract
Understanding 3D human interactions is fundamental for fine-grained scene analysis and behavioural modeling. However, most of the existing models predict incorrect, lifeless 3D estimates, that miss the subtle human contact aspects–the essence of the event–and are of little use for detailed behavioral understanding. This paper addresses such issues with several contributions: (1) we introduce models for interaction signature estimation (ISP) encompassing contact detection, segmentation, and 3D contact signature prediction; (2) we show how such components can be leveraged to ensure contact consistency during 3D reconstruction; (3) we construct several large datasets for learning and evaluating 3D contact prediction and reconstruction... (More)
Understanding 3D human interactions is fundamental for fine-grained scene analysis and behavioural modeling. However, most of the existing models predict incorrect, lifeless 3D estimates, that miss the subtle human contact aspects–the essence of the event–and are of little use for detailed behavioral understanding. This paper addresses such issues with several contributions: (1) we introduce models for interaction signature estimation (ISP) encompassing contact detection, segmentation, and 3D contact signature prediction; (2) we show how such components can be leveraged to ensure contact consistency during 3D reconstruction; (3) we construct several large datasets for learning and evaluating 3D contact prediction and reconstruction methods; specifically, we introduce CHI3D, a lab-based accurate 3D motion capture dataset with 631 sequences containing 2,525 contact events, 728,664 ground truth 3D poses, as well as FlickrCI3D, a dataset of 11,216 images, with 14,081 processed pairs of people, and 81,233 facet-level surface correspondences. Finally, (4) we propose methodology for recovering the ground-truth pose and shape of interacting people in a controlled setup and (5) annotate all 3D interaction motions in CHI3D with textual descriptions.
(Less)
- author
- Fieraru, Mihai ; Zanfir, Mihai ; Oneata, Elisabeta ; Popa, Alin Ionut ; Olaru, Vlad and Sminchisescu, Cristian LU
- organization
- publishing date
- 2025
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- 3D human reconstruction, 3D pose, interaction, motion capture, physical contact
- in
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- volume
- 47
- issue
- 12
- pages
- 12 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- external identifiers
-
- pmid:40853828
- scopus:105014352912
- ISSN
- 0162-8828
- DOI
- 10.1109/TPAMI.2025.3601974
- language
- English
- LU publication?
- yes
- id
- de378946-5287-40b7-9674-f6d9c9e4d7dc
- date added to LUP
- 2025-11-17 12:06:29
- date last changed
- 2025-11-17 12:07:25
@article{de378946-5287-40b7-9674-f6d9c9e4d7dc,
abstract = {{<p>Understanding 3D human interactions is fundamental for fine-grained scene analysis and behavioural modeling. However, most of the existing models predict incorrect, lifeless 3D estimates, that miss the subtle human contact aspects–the essence of the event–and are of little use for detailed behavioral understanding. This paper addresses such issues with several contributions: (1) we introduce models for interaction signature estimation (ISP) encompassing contact detection, segmentation, and 3D contact signature prediction; (2) we show how such components can be leveraged to ensure contact consistency during 3D reconstruction; (3) we construct several large datasets for learning and evaluating 3D contact prediction and reconstruction methods; specifically, we introduce CHI3D, a lab-based accurate 3D motion capture dataset with 631 sequences containing 2,525 contact events, 728,664 ground truth 3D poses, as well as FlickrCI3D, a dataset of 11,216 images, with 14,081 processed pairs of people, and 81,233 facet-level surface correspondences. Finally, (4) we propose methodology for recovering the ground-truth pose and shape of interacting people in a controlled setup and (5) annotate all 3D interaction motions in CHI3D with textual descriptions.</p>}},
author = {{Fieraru, Mihai and Zanfir, Mihai and Oneata, Elisabeta and Popa, Alin Ionut and Olaru, Vlad and Sminchisescu, Cristian}},
issn = {{0162-8828}},
keywords = {{3D human reconstruction; 3D pose; interaction; motion capture; physical contact}},
language = {{eng}},
number = {{12}},
pages = {{10870--10881}},
publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
series = {{IEEE Transactions on Pattern Analysis and Machine Intelligence}},
title = {{Reconstructing Three-Dimensional Models of Interacting Humans}},
url = {{http://dx.doi.org/10.1109/TPAMI.2025.3601974}},
doi = {{10.1109/TPAMI.2025.3601974}},
volume = {{47}},
year = {{2025}},
}