Quality Dynamic Human Body Modeling Using a Single Low-Cost Depth Camera

In this paper we present a novel autonomous pipeline to build a personalized parametric model (pose-driven avatar) using a single depth sensor. Our method first captures a few high-quality scans of the user rotating herself at multiple poses from different views. We fit each incomplete scan using template fitting techniques with a generic human template, and register all scans to every pose using global consistency constraints. After registration, these watertight models with different poses are used to train a parametric model in a fashion similar to the SCAPE method. Once the parametric model is built, it can be used as an animitable avatar or more interestingly synthesizing dynamic 3D models from single-view depth videos. Experimental results demonstrate the effectiveness of our system to produce dynamic models.

[1]  M. Pauly,et al.  Embedded deformation for shape manipulation , 2007, SIGGRAPH 2007.

[2]  Hans-Peter Seidel,et al.  Motion capture using joint skeleton tracking and surface estimation , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Steven M. Seitz,et al.  Spacetime faces , 2004, ACM Trans. Graph..

[4]  Luc Van Gool,et al.  Functional categorization of objects using real-time markerless motion capture , 2011, CVPR 2011.

[5]  Michael J. Black,et al.  Home 3D body scans from noisy image and range data , 2011, 2011 International Conference on Computer Vision.

[6]  Huamin Wang,et al.  Modeling deformable objects from a single depth camera , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[7]  Luc Van Gool,et al.  Online loop closure for real-time interactive 3D scanning , 2011, Comput. Vis. Image Underst..

[8]  Matthias Zwicker,et al.  Global registration of dynamic range scans for articulated model reconstruction , 2011, TOGS.

[9]  Michael J. Black,et al.  The Naked Truth: Estimating Body Shape Under Clothing , 2008, ECCV.

[10]  Luke S. Zettlemoyer,et al.  3D Wikipedia , 2013, ACM Trans. Graph..

[11]  Michael J. Black,et al.  DRAPE , 2012, ACM Trans. Graph..

[12]  Christian Rössl,et al.  Laplacian surface editing , 2004, SGP '04.

[13]  Szymon Rusinkiewicz,et al.  Estimating the Laplace‐Beltrami Operator by Restricting 3D Functions , 2009, Comput. Graph. Forum.

[14]  Leonidas J. Guibas,et al.  Robust single-view geometry and motion reconstruction , 2009, ACM Trans. Graph..

[15]  Michael M. Kazhdan,et al.  Screened poisson surface reconstruction , 2013, TOGS.

[16]  Hans-Peter Seidel,et al.  Motion capture using joint skeleton tracking and surface estimation , 2009, CVPR.

[17]  Sang Wook Lee,et al.  Multiview registration of 3D scenes by minimizing error between coordinate frames , 2002, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Jonathan T. Barron,et al.  3D self-portraits , 2013, ACM Trans. Graph..

[19]  Zicheng Liu,et al.  Tensor-Based Human Body Modeling , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[20]  Sebastian Thrun,et al.  SCAPE: shape completion and animation of people , 2005, SIGGRAPH 2005.

[21]  Andrew W. Fitzgibbon,et al.  KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera , 2011, UIST.

[22]  Ligang Liu,et al.  Scanning 3D Full Human Bodies Using Kinects , 2012, IEEE Transactions on Visualization and Computer Graphics.