000149157 001__ 149157 000149157 005__ 20251017144634.0 000149157 0247_ $$2doi$$a10.1109/WACV51458.2022.00125 000149157 0248_ $$2sideral$$a131428 000149157 037__ $$aART-2022-131428 000149157 041__ $$aeng 000149157 100__ $$0(orcid)0000-0002-8949-2632$$aPerez-Yus, A.$$uUniversidad de Zaragoza 000149157 245__ $$aMatching and Recovering 3D People From Multiple Views 000149157 260__ $$c2022 000149157 5060_ $$aAccess copy available to the general public$$fUnrestricted 000149157 5203_ $$aThis 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. 000149157 536__ $$9info:eu-repo/grantAgreement/ES/AEI/PCI2019-103386$$9info:eu-repo/grantAgreement/ES/AEI/PID2020-120049RB 000149157 540__ $$9info:eu-repo/semantics/openAccess$$aAll rights reserved$$uhttp://www.europeana.eu/rights/rr-f/ 000149157 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/acceptedVersion 000149157 700__ $$aAgudo, A. 000149157 7102_ $$15007$$2520$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Ingen.Sistemas y Automát. 000149157 773__ $$g(2022), 3622-3631$$tProceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)$$x2472-6737 000149157 8564_ $$s4588968$$uhttps://zaguan.unizar.es/record/149157/files/texto_completo.pdf$$yPostprint 000149157 8564_ $$s2773308$$uhttps://zaguan.unizar.es/record/149157/files/texto_completo.jpg?subformat=icon$$xicon$$yPostprint 000149157 909CO $$ooai:zaguan.unizar.es:149157$$particulos$$pdriver 000149157 951__ $$a2025-10-17-14:28:19 000149157 980__ $$aARTICLE