Curve Style Analysis in a Set of Shapes
COMPUTER GRAPHICS forum 2012
Honghua Li Hao Zhang Yanzhen Wang Junjie Cao Ariel Shamir Daniel Cohen-Or
Simon Fraser University National University of Defense Technology
Dalian University of Technology Interdisciplinary Center Tel Aviv University

Figure 1: Curve style analysis in a set of shapes. (a) Input set with diverse content and style. (b) Extracted curve features clustered into feature modes. (c) Construction of feature-shape association matrix (FSM) whose rows are consolidated feature modes and whose columns correspond to the set of shapes. (d) Style-content table resulting from style-content separation. (e) Style transfer applied to fill the blanks.

Abstract

The word "style" can be interpreted in so many different ways in so many different contexts. To provide a general analysis and understanding of styles is a highly challenging problem. We pose the open question "how to extract styles from geometric shapes?" and address one instance of the problem. Specifically, we present an unsupervised algorithm for identifying curve styles in a set of shapes. In our setting, a curve style is explicitly represented by a mode of curve features appearing along the 2D silhouettes of the shapes in the set. Unlike previous attempts, we do not rely on any preconceived conceptual characterizations, e.g., via specific shape descriptors, to define what is or is not a style.

Paper

High quality, 5.5MB      Low quality, 0.5MB

Acknowledgement

Foremost, we would like to thank the anonymous reviewers for their open-minded and candid comments; their valuable feedback played important roles in shaping the final version of the paper. The silhouette images were purchased from online stock photo sites shutterstock. com and bigstock.com (now part of shutterstock.com). This work is supported in part by grants from China Scholarship Council, National Science and Engineering Research Council of Canada (No. 611370), National Natural Science Foundation of China (No. 61173102 and 61173103), National Natural Science Foundation of China-Guangdong Joint Fund (No. U0935004), the Israel Ministry of Science and Education, and the Israel Science Foundation.