Estimating 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 .
@article{arxiv.2408.10805,
title = {MPL: Lifting 3D Human Pose from Multi-view 2D Poses},
author = {Seyed Abolfazl Ghasemzadeh and Alexandre Alahi and Christophe De Vleeschouwer},
journal= {arXiv preprint arXiv:2408.10805},
year = {2024}
}
Comments
14 pages, accepted in ECCV T-CAP 2024, code: https://github.com/aghasemzadeh/OpenMPL