Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
A Neural Representation of Sketch Drawings
Nov 03, 2017 (modified: Nov 03, 2017)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
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. We demonstrate that our representation is useful for computer-aided artistic work such as conditional generation, generating multiple outcomes from a partial drawing, and morphing a drawing from one class to another.
TL;DR:We investigate alternative to traditional pixel image modelling approaches, and propose a generative model for vector images.