HackerPapers

arXiv:1704.03477cs.NE

A Neural Representation of Sketch Drawings

David Ha, Douglas Eck

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.

arXiv comments
Journal reference
DOI
Subjects
cs.NENeural and Evolutionary Computing cs.LGMachine Learning stat.MLMachine Learning (Statistics)

On Hacker News

Linked by 2 identifiable commenters in 2 comments across 2 threads, from May 2017 to Jun 2026. Found in 2 HN submissions from Apr 2017 to Apr 2017. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments2 threads

  1. The disappearance of Japan's animators 1 comment

    • Nope there are models that do exactly as described, completing or elaborating on line sketches. Google had (has?) at least a couple public demos. https://arxiv.org/abs/1704.03477

      fc417fc802View on HNParent context

  2. SketchRNN model released in Magenta 1 comment

    • Link to Dataset: https://quickdraw.withgoogle.com/data Link to Blog Post announcement of Sketch-RNN code: https://magenta.tensorflow.org/sketch_rnn Link to Paper: https://arxiv.org/abs/1704.03477 Link to GitHub Repo of Sketch-RNN code…

      wei_jokView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.