Home Publications Research Grants Inventions & Patents Awards Additional Research Activities Faculties & Institutions Research Areas

Unsupervised Human Pose Estimation through Transforming Shape Templates

Schmidtke L, Vlontzos A, Ellershaw S, Lukens A, Arichi T, Kainz B (2021)

---

Publication Type: Conference contribution

Publication year: 2021

Journal

Publisher: IEEE Computer Society

Pages Range: 2484-2494

Conference Proceedings Title: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Event location: Virtual, Online, USA

ISBN: 9781665445092

DOI: 10.1109/CVPR46437.2021.00251

Abstract

Human pose estimation is a major computer vision problem with applications ranging from augmented reality and video capture to surveillance and movement tracking. In the medical context, the latter may be an important biomarker for neurological impairments in infants. Whilst many methods exist, their application has been limited by the need for well annotated large datasets and the inability to generalize to humans of different shapes and body compositions, e.g. children and infants. In this paper we present a novel method for learning pose estimators for human adults and infants in an unsupervised fashion. We approach this as a learnable template matching problem facilitated by deep feature extractors. Human-interpretable landmarks are estimated by transforming a template consisting of predefined body parts that are characterized by 2D Gaussian distributions. Enforcing a connectivity prior guides our model to meaningful human shape representations. We demonstrate the effectiveness of our approach on two different datasets including adults and infants. Project page: infantmotion.github.io.

Authors with CRIS profile

Involved external institutions

How to cite

APA:

Schmidtke, L., Vlontzos, A., Ellershaw, S., Lukens, A., Arichi, T., & Kainz, B. (2021). Unsupervised Human Pose Estimation through Transforming Shape Templates. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 2484-2494). Virtual, Online, USA: IEEE Computer Society.

MLA:

Schmidtke, Luca, et al. "Unsupervised Human Pose Estimation through Transforming Shape Templates." Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021, Virtual, Online, USA IEEE Computer Society, 2021. 2484-2494.

BibTeX: Download