| Autor: |
Yang, Lumin, Zhuang, Jiajie, Fu, Hongbo, Wei, Xiangzhi, Zhou, Kun, Zheng, Youyi |
| Rok vydání: |
2020 |
| Předmět: |
|
| Druh dokumentu: |
Working Paper |
| Popis: |
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. |
| Databáze: |
arXiv |
| Externí odkaz: |
|
