Data-Driven Physics for Human Soft Tissue Animation

ACM Transaction on Graphics (Proceedings of SIGGRAPH 2017)
Meekyoung Kim, Gerard Pons-Moll, Sergi Pujades, Seungbae Bang, Jinwook Kim, Michael Black, and
Sung-Hee Lee


Data driven models of human poses and soft-tissue deformations can produce very realistic results, but they only model the visible surface of the human body and cannot create skin deformation due to interactions with the environment. Physical simulations can generalize to external forces, but their parameters are difficult to control. In this paper, we present a layered volumetric human body model learned from data. Our model is composed of a data-driven inner layer and a physics-based external layer. The inner layer is driven with a volumetric statistical body model (VSMPL). The soft tissue layer consists of a tetrahedral mesh that is driven using the finite element method (FEM). Model parameters, namely the segmentation of the body into layers and the soft tissue elasticity, are learned directly from 4D registrations of humans exhibiting soft tissue deformations. The learned two layer model is a realistic full-body avatar that generalizes to novel motions and external forces. Experiments show that the resulting avatars produce realistic results on held out sequences and react to external forces. Moreover, the model supports the retargeting of physical properties from one avatar when they share the same topology.


[PAPER] — 5.4mb PDF


  title = {Data-Driven Physics for Human Soft Tissue Animation},
  author = {Kim, Meekyoung and Pons-Moll, Gerard and Pujades, Sergi and Bang, Seungbae and Kim, Jinwook and Black, Michael and Lee, Sung-Hee},
  journal = {ACM Transactions on Graphics, (Proc. SIGGRAPH)},
  volume = {36},
  number = {4},
  year = {2017},
  url = {}}