SCAPE: Shape Completion and Animation of People. We introduce the SCAPE method (Shape Completion and Animation for PEople)---a data-driven method for building a human shape model that spans variation in both subject shape and pose. The method is based on a representation that incorporates both articulated and non-rigid deformations. We learn a pose deformation model that derives the non-rigid surface deformation as a function of the pose of the articulated skeleton. We also learn a separate model of variation based on body shape. Our two models can be combined to produce 3D surface models with realistic muscle deformation for different people in different poses, when neither appear in the training set. We show how the model can be used for shape completion --- generating a complete surface mesh given a limited set of markers specifying the target shape. We present applications of shape completion to partial view completion and motion capture animation. In particular, our method is capable of constructing a high-quality animated surface model of a moving person, with realistic muscle deformation, using just a single static scan and a marker motion capture sequence of the person.

References in zbMATH (referenced in 28 articles )

Showing results 1 to 20 of 28.
Sorted by year (citations)

1 2 next

  1. Bai, Fang; Bartoli, Adrien: Procrustes analysis with deformations: a closed-form solution by eigenvalue decomposition (2022)
  2. He, Youzi; Li, Bin; Sheng, Tingting; Wang, Xianchao: Generating geometric body shapes with electromagnetic source scattering techniques (2020)
  3. Chen, Mingjia; Zou, Qianfang; Wang, Changbo; Liu, Ligang: EdgeNet: deep metric learning for 3D shapes (2019)
  4. Ji, Zhongping; Qi, Xiao; Wang, Yigang; Xu, Gang; Du, Peng; Wu, Xundong; Wu, Qing: Human body shape reconstruction from binary silhouette images (2019)
  5. Li, Jinghong; Liu, Hongyu; Tsui, Wing-Yan; Wang, Xianchao: An inverse scattering approach for geometric body generation: a machine learning perspective (2019)
  6. Chen, Mingjia; Wang, Changbo; Qin, Hong: Jointly learning shape descriptors and their correspondence via deep triplet cnns (2018)
  7. Dym, Nadav; Lipman, Yaron: Exact recovery with symmetries for procrustes matching (2017)
  8. Lai, Rongjie; Zhao, Hongkai: Multiscale nonrigid point cloud registration using rotation-invariant sliced-Wasserstein distance via Laplace-Beltrami eigenmap (2017)
  9. Simon, K.; Sheorey, S.; Jacobs, D. W.; Basri, R.: A hyperelastic two-scale optimization model for shape matching (2017)
  10. Dubrovina, Anastasia; Aflalo, Yonathan; Kimmel, Ron: Non-rigid shape correspondence using surface descriptors and metric structures in the spectral domain (2016)
  11. Pokrass, Jonathan; Bronstein, Alexander M.; Bronstein, Michael M.; Sprechmann, Pablo; Sapiro, Guillermo: Sparse models for intrinsic shape correspondence (2016)
  12. Chazal, Frédéric; Glisse, Marc; Labruère, Catherine; Michel, Bertrand: Convergence rates for persistence diagram estimation in topological data analysis (2015)
  13. Eslami, S. M. Ali; Heess, Nicolas; Williams, Christopher K. I.; Winn, John: The shape Boltzmann machine: a strong model of object shape (2014)
  14. Huang, Qixing; Guibas, Leonidas J.; Mitra, Niloy J.: Near-regular structure discovery using linear programming (2014)
  15. Tam, Gary K. L.; Martin, Ralph R.; Rosin, Paul L.; Lai, Yu-Kun: Diffusion pruning for rapidly and robustly selecting global correspondences using local isometry (2014)
  16. Zhang, Dianyong; Miao, Zhenjiang; Chen, Shengyong: Human model adaptation for multiview markerless motion capture (2013) ioport
  17. Zhang, Dianyong; Miao, Zhenjiang; Chen, Shengyong; Wan, Lili: Optimization and soft constraints for human shape and pose estimation based on a 3D morphable model (2013) ioport
  18. Bandouch, Jan; Jenkins, Odest Chadwicke; Beetz, Michael: A self-training approach for visual tracking and recognition of complex human activity patterns (2012) ioport
  19. Corazza, Stefano; Mündermann, Lars; Gambaretto, Emiliano; Ferrigno, Giancarlo; Andriacchi, Thomas P.: Markerless motion capture through visual hull, articulated ICP and subject specific model generation (2010) ioport
  20. Gall, Juergen; Rosenhahn, Bodo; Brox, Thomas; Seidel, Hans-Peter: Optimization and filtering for human motion capture (2010) ioport

1 2 next