A Neural Representation of Sketch Drawings

Code

• github.com/hardmaru/sketch-rnn-datasets
  tf★ 220
• github.com/alexis-jacq/Pytorch-Sketch-RNN
  pytorch★ 191
• github.com/hardmaru/sketch-rnn-flowchart
  tf★ 36
• github.com/altsoph/paranoid_transformer
  pytorch★ 19
• github.com/MarioBonse/Sketch-rnn
  tf★ 9
• github.com/Triple-L/Wartegg_test
  none★ 0
• github.com/kumnikhil/christmAIs_replica
  tf★ 0
• github.com/tosmaster/imagevision
  pytorch★ 0
• github.com/eyalzk/sketch_rnn_keras
  tf★ 0
• github.com/Ar-Kareem/sketch-RNN
  pytorch★ 0

Abstract

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.

Reproductions