@article{smplbodymodels,
  title = {SMPL and SMPL-X parametric body models},
  author = {Loper, M. and Mahmood, N. and Romero, J. and Pons-Moll, G. and Black, M. J.},
  year = {2015},
  journal = {ACM Transactions on Graphics (SIGGRAPH Asia 2015) / CVPR 2019},
  url = {https://dl.acm.org/doi/10.1145/2816795.2818013},
  abstract = {Loper et al. (2015) introduced SMPL, a parametric body model that represents a human figure as a blend of shape and pose parameters derived from a large database of body scans; the model outputs a posed mesh via learned blend shapes and skinning weights. Pavlakos et al. (2019) extended it to SMPL-X, adding articulated hands and an expressive face model for whole-body capture. Together they form the de facto output representation for learning-based human pose estimation, motion capture and text-to-motion generation: the Motion Diffusion Model, DeepPhase and most motion-synthesis methods produce SMPL parameters, making the model prerequisite knowledge for reading their outputs and results in animation research and teaching.},
  keywords = {motion-synthesis, character-animation},
  note = {AI \& Animation Education Knowledge Base}
}