Learning to Group Discrete Graphical Patterns

Zhaoliang Lun (1) , Changqing Zou (2) , Haibin Huang (1) , Evangelos Kalogerakis (3) , Ping Tan (2) , Marie-Paule Cani (4) , Hao Zhang (2)

1 UMass Amherst - University of Massachusetts [Amherst]
2 SFU.ca - Simon Fraser University = Université Simon Fraser
3 UMASS - University of Massachusetts Medical School [Worcester]
4 LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau]

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 perceptions for grouping, we train our network on a large, human-annotated dataset of pattern groupings consisting of patterns at varying granularity levels, with rich element relations and varieties, and tempered with noise and other data imperfections. Experimental results demonstrate that our deep-learned measure leads to robust grouping results.

Mots clés: CCS Concepts: • Computing methodologies → Shape analysis; Additional Key Words and Phrases: discrete pattern analysis; perceptual; grouping; supervised learning; convolutional neural networks; ACM Reference format:

Domaines: Synthèse d'image et réalité virtuelle [cs.GR]

Zhaoliang Lun, Changqing Zou, Haibin Huang, Evangelos Kalogerakis, Ping Tan, et al.. Learning to Group Discrete Graphical Patterns. ACM Transactions on Graphics, 2017, 11. ⟨hal-01703062⟩