ShapeMate: A Virtual Tape Measure

We introduce ShapeMate, a framework for human body shape estimation and classification for on-line fashion applications. Given a single image of a subject our framework is able to simultaneously estimate detailed 3D human body shape and compute foreground segmentation with minimal user input. Once the body shape has been estimated, various semantic parameters are extracted for garment size and style recommendation. Preliminary results demonstrate that a single image holds enough information for accurate shape classification.

[1]  Michael J. Black,et al.  Combined discriminative and generative articulated pose and non-rigid shape estimation , 2007, NIPS.

[2]  Andrew Blake,et al.  "GrabCut" , 2004, ACM Trans. Graph..

[3]  Yu Chen,et al.  Inferring 3D Shapes and Deformations from Single Views , 2010, ECCV.

[4]  Michael J. Black,et al.  Detailed Human Shape and Pose from Images , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

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

[6]  M. J. D. Powell,et al.  On search directions for minimization algorithms , 1973, Math. Program..

[7]  Michael J. Black,et al.  Estimating human shape and pose from a single image , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[8]  Mun Wai Lee,et al.  A model-based approach for estimating human 3D poses in static images , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Michael J. Black,et al.  Shining a Light on Human Pose: On Shadows, Shading and the Estimation of Pose and Shape , 2007, 2007 IEEE 11th International Conference on Computer Vision.