MPL: Lifting 3D Human Pose from Multi-view 2D Poses

Ghasemzadeh, Seyed Abolfazl;Alahi, Alexandre;De Vleeschouwer, Christophe
(2024) Towards a Complete Analysis of People: Fine-grained Understanding for Real-World Applications, ECCV workshop.

Files

MPL-ECCV-240810805v1.pdf
  • Open Access
  • Adobe PDF
  • 3.27 MB
Download

Details

Authors
Abstract
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.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

Ghasemzadeh, S. A., Alahi, A., & De Vleeschouwer, C. (2024). MPL: Lifting 3D Human Pose from Multi-view 2D Poses. Computer Vision - ECCV 2024 Workshops. Published. Towards a Complete Analysis of People: Fine-grained Understanding for Real-World Applications, ECCV workshop. https://hdl.handle.net/2078.5/236766 (Original work published 2024)