期刊论文、会议论文

Zou, Changqing

英文

ACM Transactions on Graphics

0730-0301

2017

36

6

225:1-225:11

10th ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia

NOV 27-30, 2017

Bangkok, THAILAND

[Lun, Zhaoliang;Huang, Haibin;Kalogerakis, Evangelos] Univ Massachusetts, Amherst, MA 01003 USA.^[Zou, Changqing;Tan, Ping;Zhang, Hao] Simon Fraser Univ, Burnaby, BC, Canada.^[Zou, Changqing] Hengyang Normal Univ, Hengyang, Peoples R China.^[Cani, Marie-Paule] CNRS, Ecole Polytech, Paris, France.

ACM SIGGRAPH

2 PENN PLAZA, STE 701, NEW YORK, NY 10121-0701 USA

ASSOC COMPUTING MACHINERY

10.1145/3130800.3130841

We thank the anonymous reviewers for their comments and Dr. Ke Li for the help on experimental data preparation. Zou acknowledges support from the Science and Technology Plan Project of Hunan Province (Grant No.: 2016TP1020) and the Program of Key Disciplines in Hunan Province. Kalogerakis acknowledges support from NSF (Grant No.: CHS-1422441 and CHS-1617333), and the Massachusetts Technology Collaborative grant for funding the UMass GPU cluster. Tan acknowledges support from NSERC Canada (Grant No.: 31-611663 and 31-611664). Zhang acknowledges support from NSERC Canada (Grant No.: 611370 and 611649), and gift funds from Adobe Research.

本校为通讯机构

We introduce a deep learning approach for grouping discrete patterns common in graphical designs. Our approach is based on a convolutional neural network architecture that learns a grouping measure defined over a pair of pattern elements. Motivated by perceptual grouping principles, the key feature of our network is the encoding of element shape, context, symmetries, and structural arrangements. These element properties are all jointly considered and appropriately weighted in our grouping measure. To better align our measure with human percepti...