SketchGNN : Semantic Sketch Segmentation with Graph Neural Networks

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

3 Scopus Citations
View graph of relations

Author(s)

  • Lumin YANG
  • Jiajie ZHUANG
  • Xiangzhi WEI
  • Kun ZHOU
  • Youyi ZHENG

Related Research Unit(s)

Detail(s)

Original languageEnglish
Article number28
Journal / PublicationACM Transactions on Graphics
Volume40
Issue number3
Publication statusPublished - Jun 2021

Link(s)

Abstract

We introduce SketchGNN, a convolutional graph neural network for semantic segmentation and labeling of freehand vector sketches. We treat an input stroke-based sketch as a graph, with nodes representing the sampled points along input strokes and edges encoding the stroke structure information. To predict the per-node labels, our SketchGNN uses graph convolution and a static-dynamic branching network architecture to extract the features at three levels, i.e., point-level, stroke-level, and sketch-level. SketchGNN significantly improves the accuracy of the state-of-the-art methods for semantic sketch segmentation (by 11.2% in the pixel-based metric and 18.2% in the component-based metric over a large-scale challenging SPG dataset) and has magnitudes fewer parameters than both image-based and sequence-based methods.

Research Area(s)

  • sketch analysis, semantic segmentation, deep learning

Citation Format(s)

SketchGNN : Semantic Sketch Segmentation with Graph Neural Networks. / YANG, Lumin; ZHUANG, Jiajie; FU, Hongbo; WEI, Xiangzhi; ZHOU, Kun; ZHENG, Youyi.

In: ACM Transactions on Graphics, Vol. 40, No. 3, 28, 06.2021.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

Download Statistics

No data available