Login | Register

Parametric design for human body modeling by wireframe-assisted deep learning


Parametric design for human body modeling by wireframe-assisted deep learning

Kwok, Tsz-Ho ORCID: https://orcid.org/0000-0001-7240-1426, Huang, Jida and Zhou, Chi (2019) Parametric design for human body modeling by wireframe-assisted deep learning. Computer-Aided Design, 108 . pp. 19-29. ISSN 00104485 (In Press)

Text (application/pdf)
Kwok 2018.pdf - Accepted Version
Restricted to Repository staff only until 8 November 2020.
Available under License Spectrum Terms of Access.

Official URL: http://dx.doi.org/10.1016/j.cad.2018.10.004


Statistical learning of human body shape can be used for reconstructing or estimating body shapes from incomplete data, semantic parametric design, modifying images and videos, or simulation. A digital human body is normally represented in a high-dimensional space, and the number of vertices in a mesh is far larger than the number of human bodies in public available databases, which results in a model learned by Principle Component Analysis (PCA) can hardly reflect the true variety in human body shapes. While deep learning has been most successful on data with an underlying Euclidean or grid-like structure, the geometric nature of human body is non-Euclidean, it will be very challenging to perform deep learning techniques directly on such non-Euclidean domain. This paper presents a deep neural network (DNN) based hierarchical method for statistical learning of human body by using feature wireframe as one of the layers to separate the whole problem into smaller and more solvable sub-problems. The feature wireframe is a collection of feature curves which are semantically defined on the mesh of human body, and it is consistent to all human bodies. A set of patches can then be generated by clustering the whole mesh surface to separated ones that interpolate the feature wireframe. Since the surface is separated into patches, PCA only needs to be conducted on each patch but not on the whole surface. The spatial relationships between the semantic parameter, the wireframe and the patches are learned by DNN and linear regression respectively. An application of semantic parametric design is used to demonstrate the capability of the method, where the semantic parameters are linked to the feature wireframe instead of the mesh directly. Under this hierarchy, the feature wireframe acts like an agent between semantic parameters and the mesh, and also contains semantic meaning by itself. The proposed method of learning human body statistically with the help of feature wireframe is scalable and has a better quality.

Divisions:Concordia University > Gina Cody School of Engineering and Computer Science > Mechanical, Industrial and Aerospace Engineering
Item Type:Article
Authors:Kwok, Tsz-Ho and Huang, Jida and Zhou, Chi
Journal or Publication:Computer-Aided Design
  • Natural Sciences & Engineering Research Council of Canada (NSERC)
  • National Science Foundation (NSF)
Digital Object Identifier (DOI):10.1016/j.cad.2018.10.004
Keywords:Feature; Wireframe; Human body; Deep learning; Parametric design
ID Code:984703
Deposited By: ALINE SOREL
Deposited On:27 Nov 2018 19:54
Last Modified:27 Nov 2018 19:54


Kwok T.-H., Zhang Y., Wang C.C.L., Liu Y., Tang K. Styling evolution for tight-fitting garments, IEEE Trans Vis Comput Graphics, 22 (5) (2016), pp. 1580-1591

Anguelov D., Srinivasan P., Koller D., Thrun S., Rodgers J., Davis J. SCAPE: Shape completion and animation of people, ACM Trans Graph, 24 (3) (2005), pp. 408-416

Hasler N., Stoll C., Sunkel M., Rosenhahn B., Seidel H.-P. A statistical model of human pose and body shape, Comput Graph Forum, 28 (2) (2009), pp. 337-346

Chu C.-H., Tsai Y.-T., Wang C.C., Kwok T.-H. Exemplar-based statistical model for semantic parametric design of human body, Comput Ind, 61 (6) (2010), pp. 541-549

LeCun Y., Bengio Y., Hinton G. Deep learning Nature, 521 (2015) 436 E

Bronstein M.M., Bruna J., LeCun Y., Szlam A., Vandergheynst P. Geometric deep learning: going beyond euclidean data, IEEE Signal Process Mag, 34 (4) (2017), pp. 18-42

Liu B, Wei Y, Zhang Y, Yang Q. Deep neural networks for high dimension, low sample size data. In: Proceedings of the twenty-sixth international joint conference on artificial intelligence; 2017. p. 2287 93.

Wang C.C.L. Parameterization and parametric design of mannequins, Comput Aided Des, 37 (1) (2005), pp. 83-98

Wang S., Qin S., Guan C. Feature-based human model for digital apparel design, IEEE Trans Autom Sci Eng, 11 (2) (2014), pp. 620-626

Kwok T.H., Zhang Y., Wang C.C.L. Efficient optimization of common base domains for cross parameterization, IEEE Trans Vis Comput Graphics, 18 (10) (2012), pp. 1678-1692

Wang C.C., Tang K. Pattern computation for compression garment by a physical/geometric approach, Comput Aided Des, 42 (2) (2010), pp. 78-86

Hasler N., Stoll C., Rosenhahn B., Thormählen T., Seidel H.-P. Estimating body shape of dressed humans, Comput Graph, 33 (3) (2009), pp. 211-216

Li J., Ye J., Wang Y., Bai L., Lu G. Fitting 3D garment models onto individual human models, Comput Graph, 34 (6) (2010), pp. 742-755

Pons-Moll G., Pujades S., Hu S., Black M.J. ClothCap: Seamless 4D clothing capture and retargeting, ACM Trans Graph, 36 (4) (2017), pp. 73:1-73:15

Baek S.-Y., Lee K. Parametric human body shape modeling framework for human-centered product design, Comput Aided Des, 44 (1) (2012), pp. 56-67

Au C.K., Ma Y.-S. Garment pattern definition, development and application with associative feature approach, Comput Ind, 61 (6) (2010), pp. 524-531

Chu C.-H., Wang I.-J., Wang J.B., Luh Y.-P. 3D parametric human face modeling for personalized product design: Eyeglasses frame design case, Adv Eng Inf, 32 (Suppl. C) (2017), pp. 202-223

Huang S.-H., Yang Y.-I., Chu C.-H. Human-centric design personalization of 3d glasses frame in markerless augmented reality, Adv Eng Inf, 26 (1) (2012), pp. 35-45

Hasler N., Thormählen T., Rosenhahn B., Seidel H.P. Learning skeletons for shape and pose, Proceedings of the 2010 ACM SIGGRAPH symposium on interactive 3D graphics and games, I3D ’10, ACM, New York, NY, USA (2010), pp. 23-30

Toshev A, Szegedy C. Deep Pose: Human pose estimation via deep neural networks. In The IEEE conference on computer vision and pattern recognition; 2014.

Shotton J., Sharp T., Kipman A., Fitzgibbon A., Finocchio M., Blake A., et al. Real-time human pose recognition in parts from single depth images, Commun ACM, 56 (1) (2013), pp. 116-124

Si W., Lee S.-H., Sifakis E., Terzopoulos D. Realistic biomechanical simulation and control of human swimming, ACM Trans Graph, 34 (1) (2014), pp. 10:1-10:15

Ufuk C, O. YI, Tolga C. Example-based retargeting of human motion to arbitrary mesh models. Comput Graph Forum 34(1):216–27.

Streuber S., Quiros-Ramirez M.A., Hill M.Q., Hahn C.A., Zuffi S., O’Toole A., et al. Body talk: Crowdshaping realistic 3D avatars with words, ACM Trans Graph, 35 (4) (2016), pp. 54:1-54:14

Allen B., Curless B., Popović Z. The space of human body shapes: Reconstruction and parameterization from range scans, ACM Trans Graph, 22 (3) (2003), pp. 587-594

Saito S., Zhou Z.Y., Kavan L. Computational bodybuilding: Anatomically-based modeling of human bodies, ACM Trans Graph, 34 (4) (2015), pp. 41:1-41:12

Seo H., Magnenat-Thalmann N .An example-based approach to human body manipulation, Graph Models, 66 (1) (2004), pp. 1-23

Boscaini D., Masci J., Rodolà E., Bronstein M. Learning shape correspondence with anisotropic convolutional neural networks, Advances in neural information processing systems (2016), pp. 3189-3197

Nair V., Hinton G.E. Rectified linear units improve restricted boltzmann machines, Proceedings of the 27th international conference on international conference on machine Learning, Omnipress, USA (2010), pp. 807-814

Hinton G.E., Srivastava N., Krizhevsky A., Sutskever I., Salakhutdinov R.R. Improving neural networks by preventing co-adaptation of feature detectors (2012), arXiv preprint arXiv:1207.0580

Srivastava N., Hinton G., Krizhevsky A., Sutskever I., Salakhutdinov R. Dropout: A simple way to prevent neural networks from overfitting, J Mach Learn Res, 15 (2014), pp. 1929-1958

Ioffe S., Szegedy C Batch normalization: Accelerating deep network training by reducing internal covariate shift (2015), arXiv preprint arXiv:1502.03167

Kingma D.P., Ba J. Adam: A method for stochastic optimization (2014), arXiv preprint arXiv:1412.6980
Sarris N., Strintzis M.G. 3D modeling and animation: Synthesis and analysis techniques for the human body, IGI Global (2005)

Zhang Y., Zheng J., Magnenat-Thalmann N. Example-guided anthropometric human body modeling, Vis Comput, 31 (12) (2015), pp. 1615-1631
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Downloads per month over past year

Back to top Back to top