149157 20251017144634.0 doi 10.1109/WACV51458.2022.00125 sideral 131428 ART-2022-131428 eng Perez-Yus, A. Universidad de Zaragoza (orcid)0000-0002-8949-2632 Matching and Recovering 3D People From Multiple Views 2022 Access copy available to the general public Unrestricted This paper introduces an approach to simultaneously match and recover 3D people from multiple calibrated cameras. To this end, we present an affinity measure between 2D detections across different views that enforces an uncertainty geometric consistency. This similarity is then exploited by a novel multi-view matching algorithm to cluster the detections, being robust against partial observations as well as bad detections and without assuming any prior about the number of people in the scene. After that, the multi-view correspondences are used in order to efficiently infer the 3D pose of each body by means of a 3D pictorial structure model in combination with physico-geometric constraints. Our algorithm is thoroughly evaluated on challenging scenarios where several human bodies are performing different activities which involve complex motions, producing large occlusions in some views and noisy observations. We outperform state-of-the-art results in terms of matching and 3D reconstruction. info:eu-repo/grantAgreement/ES/AEI/PCI2019-103386 info:eu-repo/grantAgreement/ES/AEI/PID2020-120049RB info:eu-repo/semantics/openAccess All rights reserved http://www.europeana.eu/rights/rr-f/ info:eu-repo/semantics/article info:eu-repo/semantics/acceptedVersion Agudo, A. 5007 520 Universidad de Zaragoza Dpto. Informát.Ingenie.Sistms. Área Ingen.Sistemas y Automát. (2022), 3622-3631 Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2472-6737 4588968 http://zaguan.unizar.es/record/149157/files/texto_completo.pdf Postprint 2773308 http://zaguan.unizar.es/record/149157/files/texto_completo.jpg?subformat=icon icon Postprint oai:zaguan.unizar.es:149157 articulos driver 2025-10-17-14:28:19 ARTICLE