Title :
Shape Deformation Using Skeleton Correspondences for Realistic Posed Fashion Flat Creation
Author :
Xianmei Wan ; Mok, P.Y. ; Xiaogang Jin
Author_Institution :
State Key Lab. of CAD&CG, Zhejiang Univ., Hangzhou, China
Abstract :
We propose a 2D shape deformation method to fit technical drawings of garments (“flats”) to body figure drawings with a diversity of fashion poses. We first dress a flat onto a body figure in a standard standing pose using Radial Basis Function (RBF) mapping. For different types of clothing, we suggest two levels of treatment to determine handles automatically. We deform the flats using the selected handles to create realistic fashion sketches that fit the garments onto fashion figures in different poses. Shape deformation is performed to minimize the distortion of all the triangles of the garment mesh and preserve garment properties in the deformation. Finally, the garment details, such as style lines and seams, are deformed accordingly for realistic deformation results. Experimental results have shown that our method can deform various garment flats to fit fashion figures in different poses.
Keywords :
clothing; deformation; pose estimation; radial basis function networks; shape recognition; 2D shape deformation; RBF mapping; body figure drawings; clothing; fashion figures; fashion pose diversity; garment flats; garment mesh; garment properties; radial basis function mapping; realistic posed fashion flat creation; skeleton correspondences; standard standing pose; Clothing; Color; Educational institutions; Shape; Skeleton; Solid modeling; Three-dimensional displays; As-rigid-as possible; fashion design; shape deformation; skeleton-based correspondence deformation;
Journal_Title :
Automation Science and Engineering, IEEE Transactions on
DOI :
10.1109/TASE.2013.2296554