A Neural Representation of Sketch Drawings

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.

Cited by in corpus (19)

• Friend, Collaborator, Student, Manager: How Design of an AI-Driven Game Level Editor Affects Creators
• Neuralogram: A Deep Neural Network Based Representation for Audio Signals
• Sketchforme: Composing Sketched Scenes from Text Descriptions for Interactive Applications
• PaintBot: A Reinforcement Learning Approach for Natural Media Painting
• Teaching GANs to Sketch in Vector Format
• Photo-Sketching: Inferring Contour Drawings from Images
• NeuNetS: An Automated Synthesis Engine for Neural Network Design
• Session-based Sequential Skip Prediction via Recurrent Neural Networks
• Learning Neurosymbolic Generative Models via Program Synthesis
• Mechanisms of Artistic Creativity in Deep Learning Neural Networks
• Trick or TReAT: Thematic Reinforcement for Artistic Typography
• Coevo: a collaborative design platform with artificial agents
• VMAV-C: A Deep Attention-based Reinforcement Learning Algorithm for Model-based Control
• Geometric Losses for Distributional Learning
• Deep Learning for Identifying Potential Conceptual Shifts for Co-creative Drawing
• Spatiotemporal Data Fusion for Precipitation Nowcasting
• LiveSketch: Query Perturbations for Guided Sketch-based Visual Search
• Processsing Simple Geometric Attributes with Autoencoders
• Generating the support with extreme value losses