VoxelKeypointFusion: generalizable multi-view multi-person pose estimation

  • In the rapidly evolving field of computer vision, the task of accurately estimating the poses of multiple individuals from various viewpoints presents a formidable challenge, especially if the estimations should be reliable as well. This work presents an extensive evaluation of the generalization capabilities of multi-view multi-person pose estimators to unseen datasets and presents a new algorithm with strong performance in this task. It also studies the improvements by additionally using depth information. Since the new approach can not only generalize well to unseen datasets, but also to different keypoints, the first multi-view multi-person whole-body estimator is presented. To support further research on those topics, all of the work is publicly accessible.

Download full text files

Export metadata

Statistics

Number of document requests

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Author:Daniel BermuthGND, Alexander PoeppelORCiDGND, Wolfgang ReifORCiDGND
URN:urn:nbn:de:bvb:384-opus4-1202904
Frontdoor URLhttps://opus.bibliothek.uni-augsburg.de/opus4/120290
URL:https://arxiv.org/abs/2410.18723
Parent Title (English):arXiv
Publisher:arXiv
Type:Preprint
Language:English
Date of Publication (online):2025/03/13
Year of first Publication:2024
Publishing Institution:Universität Augsburg
Release Date:2025/03/14
Tag:multi-view multi-person human pose estimation
Issue:arXiv:2410.18723
Institutes:Fakultät für Angewandte Informatik
Fakultät für Angewandte Informatik / Institut für Informatik
Fakultät für Angewandte Informatik / Institut für Software & Systems Engineering
Fakultät für Angewandte Informatik / Institut für Informatik / Lehrstuhl für Softwaretechnik
Fakultät für Angewandte Informatik / Institut für Informatik / Lehrstuhl für Softwaretechnik / Lehrstuhl für Softwaretechnik
Dewey Decimal Classification:0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
Licence (German):License LogoCC-BY-SA 4.0: Creative Commons: Namensnennung - Weitergabe unter gleichen Bedingungen (mit Print on Demand)