SketchGNN: Semantic Sketch Segmentation with Graph Neural Networks

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 pre...

Full description

Saved in:
Bibliographic Details
Published in:ACM transactions on graphics 2021-06, Vol.40 (3), p.1-13, Article 28
Main Authors: Yang, Lumin, Zhuang, Jiajie, Fu, Hongbo, Wei, Xiangzhi, Zhou, Kun, Zheng, Youyi
Format: Article
Language:English
Subjects:
Artificial intelligence
Computing methodologies
Non-photorealistic rendering
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:0730-0301
1557-7368
DOI:10.1145/3450284