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.
Fichier principal
zou_siga17_group.pdf (11.22 Mo)
Télécharger le fichier
zou_siga17_group-picture.png (153.27 Ko)
Télécharger le fichier
Origin | Publisher files allowed on an open archive |
---|
Format | Figure, Image |
---|
Loading...