Learning to Group Discrete Graphical Patterns

Abstract : 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.
Type de document :
Article dans une revue
ACM Trans. Graph, 2017, 11
Liste complète des métadonnées

Littérature citée [47 références]  Voir  Masquer  Télécharger


https://hal.inria.fr/hal-01703062
Contributeur : Marie-Paule Cani <>
Soumis le : mercredi 7 février 2018 - 14:34:28
Dernière modification le : jeudi 10 mai 2018 - 02:06:49
Document(s) archivé(s) le : vendredi 4 mai 2018 - 07:08:13

Fichiers

zou_siga17_group.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

  • HAL Id : hal-01703062, version 1

Citation

Zhaoliang Lun, Changqing Zou, Haibin Huang, Evangelos Kalogerakis, Ping Tan, et al.. Learning to Group Discrete Graphical Patterns. ACM Trans. Graph, 2017, 11. 〈hal-01703062〉

Partager

Métriques

Consultations de la notice

182

Téléchargements de fichiers

71