Abstract: We present sketch-rnn, a recurrent neural network able to construct stroke-based drawings of common objects. The model is trained on a dataset of human-drawn images representing many different classes. We outline a framework for conditional and unconditional sketch generation, and describe new robust training methods for generating coherent sketch drawings in a vector format.
TL;DR: We investigate alternative to traditional pixel image modelling approaches, and propose a generative model for vector images.
Keywords: applications, image modelling, computer-assisted, drawing, art, creativity, dataset
Code: [![Papers with Code](/images/pwc_icon.svg) 19 community implementations](https://paperswithcode.com/paper/?openreview=Hy6GHpkCW)
Data: [Quick, Draw! Dataset](https://paperswithcode.com/dataset/quick-draw-dataset)
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 17 code implementations](https://www.catalyzex.com/paper/arxiv:1704.03477/code)