Ghasemzadeh, Seyed AbolfazlAlahi, AlexandreDe Vleeschouwer, Christophe2025-06-092025-06-092025-07-082025-06-062024-10-2510.1007/978-3-031-91575-8_32-s2.0-105006893333https://infoscience.epfl.ch/handle/20.500.14299/251153Estimating 3D human poses from 2D images is challenging due to occlusions and projective acquisition. Learning-based approaches have been largely studied to address this challenge, both in single and multi-view setups. These solutions however fail to generalize to real-world cases due to the lack of (multi-view) ‘in-the-wild’ images paired with 3D poses for training. For this reason, we propose combining 2D pose estimation, for which large and rich training datasets exist, and 2D-to-3D pose lifting, using a transformer-based network that can be trained from synthetic 2D-3D pose pairs. Our experiments demonstrate decreases up to 45% in MPJPE errors compared to the 3D pose obtained by triangulating the 2D poses. The framework’s source code is available at https://github.com/aghasemzadeh/OpenMPL.enfalse3D Human Pose EstimationDeploymentMulti-viewtext::conference output::conference proceedings::conference paper