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.
Document type :
Journal articles
Complete list of metadatas

Cited literature [47 references]  Display  Hide  Download


https://hal.inria.fr/hal-01703062
Contributor : Marie-Paule Cani <>
Submitted on : Wednesday, February 7, 2018 - 2:34:28 PM
Last modification on : Wednesday, September 18, 2019 - 4:36:03 PM
Long-term archiving on : Friday, May 4, 2018 - 7:08:13 AM

Files

zou_siga17_group.pdf
Publisher files allowed on an open archive

Identifiers

  • 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 Transactions on Graphics, Association for Computing Machinery, 2017, 11. ⟨hal-01703062⟩

Share

Metrics

Record views

327

Files downloads

322