BézierSketch: A generative model for scalable vector sketches

Song, Yi-Zhe (2020) BézierSketch: A generative model for scalable vector sketches In: ECCV 2020, 2020-08-23-2020-08-28, Glasgow, Scotland, UK.

Preview

Text b_ziersketch_a_generative_model_for_scalable_vector_sketches.pdf - Accepted version Manuscript Download (2MB) | Preview

Abstract

The study of neural generative models of human sketches is a fascinating contemporary modeling problem due to the links between sketch image generation and the human drawing process. The landmark SketchRNN provided breakthrough by sequentially generating sketches as a sequence of waypoints. However this leads to low-resolution image generation, and failure to model long sketches. In this paper we present B´ezierSketch, a novel generative model for fully vector sketches that are automatically scalable and high-resolution. To this end, we first introduce a novel inverse graphics approach to stroke embedding that trains an encoder to embed each stroke to its best fit B´ezier curve. This enables us to treat sketches as short sequences of paramaterized strokes and thus train a recurrent sketch generator with greater capacity for longer sketches, while producing scalable high-resolution results. We report qualitative and quantitative results on the Quick, Draw! benchmark.

Item Type:	Conference or Workshop Item (Conference Poster)
Divisions :	Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :	Name Email ORCID Song, Yi-Zhe y.song@surrey.ac.uk
Date :	2 July 2020
DOI :	10.1007/978-3-030-58621-8
Copyright Disclaimer :	Copyright 2020 Springer Nature Switzerland AG
Uncontrolled Keywords :	Sketch generation; Scalable graphics; B´ezier curve
Related URLs :	Publisher Organisation
Depositing User :	Diane Maxfield
Date Deposited :	07 Oct 2020 15:15
Last Modified :	07 Oct 2020 15:15
URI:	http://epubs.surrey.ac.uk/id/eprint/858705

Actions (login required)

View Item

Downloads