Real-Time Reshaping of Humans

We present a system for real-time deformation of the shape and appearance of people who are standing in front of a depth+RGB camera, such as the Microsoft Kinect. Our system allows manipulating human body shape parameters such as height, muscularity, weight, waist girth and leg length. The manipulated appearance is displayed in realtime. Thus, instead of posing in front a real mirror and visualizing their appearance, users can pose in front of a 'virtual mirror' and visualize themselves in different body shapes. Our system is made possible by a morphable model of 3D human shape that was learnt from a large database of 3D scans of people in various body shapes and poses. In an initialization step, which lasts a couple of seconds, this model is fit to the 3D shape parameters of the people as observed in the depth data. Then, a succession of pose tracking, body segmentation, shape deformation and image warping steps are performed -- in real-time and independently for multiple people. We present a variety of results in the paper and the video, showing the interactive virtual mirror cabinet experience.

[1]  Anna Hilsmann,et al.  Tracking and Retexturing Cloth for Real-Time Virtual Clothing Applications , 2009, MIRAGE.

[2]  M. Teschner,et al.  Meshless deformations based on shape matching , 2005, SIGGRAPH 2005.

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

[4]  Marie-Pierre Jolly,et al.  Interactive Graph Cuts for Optimal Boundary and Region Segmentation of Objects in N-D Images , 2001, ICCV.

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

[6]  Hans-Peter Seidel,et al.  A Statistical Model of Human Pose and Body Shape , 2009, Comput. Graph. Forum.

[7]  Jitendra Malik,et al.  Tracking people with twists and exponential maps , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[8]  Hans-Peter Seidel,et al.  MovieReshape: tracking and reshaping of humans in videos , 2010, ACM Trans. Graph..

[9]  Marie-Pierre Jolly,et al.  Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[10]  Emiliano Gambaretto,et al.  Markerless Motion Capture through Visual Hull, Articulated ICP and Subject Specific Model Generation , 2010, International Journal of Computer Vision.

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

[12]  D. Cohen-Or,et al.  Parametric reshaping of human bodies in images , 2010, ACM Trans. Graph..