SketchGCN: Semantic Sketch Segmentation with Graph Convolutional Networks.
Year: 2020
Type: preprint
Abstract: We introduce SketchGCN, a graph convolutional neural network for semantic segmentation and labeling of free-hand sketches. We treat an input sketch as a 2D pointset, and encode the stroke structure information into graph node/edge representations. To predict the per-point labels, our SketchGCN uses graph convolution and a global-local branching network architecture to extract both intra-stroke and inter-stroke features. SketchGCN significantly improves the accuracy of the state-of-the-art methods for semantic sketch segmentation (by 11.4% in the pixel-basedmetric 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.
Source: arXiv (Cornell University)
Authors: Lumin Yang, Jiajie Zhuang, Hongbo Fu, Kun Zhou, Youyi Zheng
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3008128252