Bitmap or Vector? A study on sketch representations for deep stroke segmentation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2019

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

Abstract

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.
Fichier principal
Vignette du fichier
Sketch_DL_paper.pdf (1.59 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02922043 , version 1 (31-08-2020)

Identifiers

  • HAL Id : hal-02922043 , version 1

Cite

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⟩
198 View
242 Download

Share

Gmail Facebook Twitter LinkedIn More