Style-Content Separation by Anisotropic Part Scales

Kai Xu1,2,       Honghua Li1,2,       Hao Zhang1,       Daniel Cohen-Or3,       Yueshan Xiong2,       Zhiquan Cheng2
1Simon Fraser University       2National University of Defense Technology       3Tel-Aviv University

ACM Transactions on Graphics (SIGGRAPH Asia 2010), 29(5)



We perform co-analysis of a set of man-made 3D objects to allow the creation of novel instances derived from the set. We analyze the objects at the part level and treat the anisotropic part scales as a shape style. The co-analysis then allows style transfer to synthesize new objects. The key to co-analysis is part correspondence, where a major challenge is the handling of large style variations and diverse geometric content in the shape set. We propose style-content separation as a means to address this challenge. Specifically, we define a correspondence-free style signature for style clustering. We show that confining analysis to within a style cluster facilitates tasks such as co-segmentation, content classification, and deformation-driven part correspondence. With part correspondence between each pair of shapes in the set, style transfer can be easily performed. We demonstrate our analysis and synthesis results on several sets of man-made objects with style and content variations.



 
Figure A: A gallery of tables (row: style; column: content) for six data sets: hummers, airplanes, tables, kitchen utensils, goblets, and humanoid bodies. Newly synthesized models (in gold) fill the tables.

 

Figure B: Results of co-segmentation and D2F-based inter-style part correspondence on three subsets (a-c) of the chair and stool set. In each subset, models are grouped by style clusters.

 

  @article {xu_siga10,
title = {Style-Content Separation by Anisotropic Part Scales},
author = {Kai Xu and Honghua Li and Hao Zhang and Daniel Cohen-Or and Yueshan Xiong and Zhiquan Cheng}
journal = {ACM Transactions on Graphics, (Proc. of SIGGRAPH Asia 2010)},
volume = {29},
number = {5},
pages = {to appear},
year = {2010}
  }

[ Top | Home ]