Bitmap or Vector? A study on sketch representations for deep stroke segmentation

F Hähnlein (1, 2) , Y Gryaditskaya (1, 2) , A Bousseau (1, 2)

1 UniCA - Université Côte d'Azur
2 GRAPHDECO - GRAPHics and DEsign with hEterogeneous COntent

Deep learning achieves impressive performances on image segmentation, which has motivated the recent development of deep neural networks for the related task of sketch segmentation, where the goal is to assign labels to the different strokes that compose a line drawing. However, while natural images are well represented as bitmaps, line drawings can also be represented as vector graphics, such as point sequences and point clouds. In addition to offering different trade-offs on resolution and storage, vector representations often come with additional information, such as stroke ordering and speed. In this paper, we evaluate three crucial design choices for sketch segmentation using deep-learning : which sketch representation to use, which information to encode in this representation, and which loss function to optimize. Our findings suggest that point clouds represent a competitive alternative to bitmaps for sketch segmentation, and that providing extra-geometric information improves performance.

Mots clés: Sketch segmentation; Deep-learning; Point clouds; Vector graphics

Domaines: Intelligence artificielle [cs.AI]; Ingénierie assistée par ordinateur; Apprentissage [cs.LG]; Traitement des images [eess.IV]

F Hähnlein, Y Gryaditskaya, A Bousseau. Bitmap or Vector? A study on sketch representations for deep stroke segmentation. Journées Francaises d'Informatique Graphique et de Réalité virtuelle, Nov 2019, Marseille, France. ⟨hal-02922043⟩