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.

We introduce SketchGCN, a graph convolutional neural network for semantic segmentation and labeling of freehand sketches. We treat an input sketch as a 2D point set, and encode the stroke structure information into graph node/edge representations. To predict the per-point labels, our SketchGCN uses graph convolution and a globallocal branching network architecture to extract both intrastroke 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-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 sequencebased methods.

Controlling stroke size in Fast Style Transfer remains a difficult task. So far, only a few attempts have been made towards it, and they still exhibit several deficiencies regarding efficiency, flexibility, and diversity. In this paper, we aim to tackle these problems and propose a recurrent convolutional neural subnetwork, which we call recurrent stroke‐pyramid, to control the stroke size in Fast Style Transfer. Compared to the state‐of‐the‐art methods, our method not only achieves competitive results with much fewer parameters but provides more flexibility and efficiency for generalizing to unseen larger stroke size and being able to produce a wide range of stroke sizes with only one residual unit. We further embed the recurrent stroke‐pyramid into the Multi‐Styles and the Arbitrary‐Style models, achieving both style and stroke‐size control in an entirely feed‐forward manner with two novel run‐time control strategies.