A Neural Representation of Sketch Drawings

04/11/2017
by   David Ha, et al.
0

We present sketch-rnn, a recurrent neural network (RNN) able to construct stroke-based drawings of common objects. The model is trained on thousands of crude human-drawn images representing hundreds of 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

08/26/2021

SketchLattice: Latticed Representation for Sketch Manipulation

The key challenge in designing a sketch representation lies with handlin...
09/13/2017

Sketch-pix2seq: a Model to Generate Sketches of Multiple Categories

Sketch is an important media for human to communicate ideas, which refle...
11/20/2018

Sketch-R2CNN: An Attentive Network for Vector Sketch Recognition

Freehand sketching is a dynamic process where points are sequentially sa...
11/09/2020

Sketch-Inspector: a Deep Mixture Model for High-Quality Sketch Generation of Cats

With the involvement of artificial intelligence (AI), sketches can be au...
08/11/2016

Enabling My Robot To Play Pictionary : Recurrent Neural Networks For Sketch Recognition

Freehand sketching is an inherently sequential process. Yet, most approa...
08/27/2020

SketchEmbedNet: Learning Novel Concepts by Imitating Drawings

Sketch drawings are an intuitive visual domain that appeals to human ins...
11/15/2018

Sketch based Reduced Memory Hough Transform

This paper proposes using sketch algorithms to represent the votes in Ho...

Code Repositories

Pytorch-Sketch-RNN

a pytorch implementation of https://arxiv.org/abs/1704.03477


view repo