CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms

Abstract

We propose a new system for generating art. The system generates art by looking at art and learning about style; and becomes creative by increasing the arousal potential of the generated art by deviating from the learned styles. We build over Generative Adversarial Networks (GAN), which have shown the ability to learn to generate novel images simulating a given distribution. We argue that such networks are limited in their ability to generate creative products in their original design. We propose modifications to its objective to make it capable of generating creative art by maximizing deviation from established styles and minimizing deviation from art distribution. We conducted experiments to compare the response of human subjects to the generated art with their response to art created by artists. The results show that human subjects could not distinguish art generated by the proposed system from art generated by contemporary artists and shown in top art fairs. Human subjects even rated the generated images higher on various scales.

This paper is an extended version of a paper published on the eighth International Conference on Computational Creativity (ICCC), held in Atlanta, GA, June 20th-June 22nd, 2017

References in corpus (1)

• Empirical Evaluation of Rectified Activations in Convolutional Network

Cited by in corpus (42)

• Detecting Visual Design Principles in Art and Architecture through Deep Convolutional Neural Networks
• High-Resolution Mammogram Synthesis using Progressive Generative Adversarial Networks
• Creativity and Machine Learning: A Survey
• Neural Painters: A learned differentiable constraint for generating brushstroke paintings
• A deep learning approach to clustering visual arts
• Learning to Sketch with Deep Q Networks and Demonstrated Strokes
• Secure Deep Learning Engineering: A Software Quality Assurance Perspective
• Structured Variational Inference for Simulating Populations of Radio Galaxies
• End-to-End Chinese Landscape Painting Creation Using Generative Adversarial Networks
• Diverse Multimedia Layout Generation with Multi Choice Learning
• From Artificial Neural Networks to Deep Learning for Music Generation -- History, Concepts and Trends
• A Brief Introduction to Generative Models
• Fingerprint Spoof Generalization
• Machine learning based co-creative design framework
• Discovering Visual Patterns in Art Collections with Spatially-consistent Feature Learning
• Generative Art Using Neural Visual Grammars and Dual Encoders
• Learning from Multi-domain Artistic Images for Arbitrary Style Transfer
• Generalization and Memorization: The Bias Potential Model
• KG-GAN: Knowledge-Guided Generative Adversarial Networks
• Active Divergence with Generative Deep Learning -- A Survey and Taxonomy
• Dialog on a canvas with a machine
• CMTS: Conditional Multiple Trajectory Synthesizer for Generating Safety-critical Driving Scenarios
• IAN: Combining Generative Adversarial Networks for Imaginative Face Generation
• Can GAN originate new electronic dance music genres? -- Generating novel rhythm patterns using GAN with Genre Ambiguity Loss
• Predicting Opioid Relapse Using Social Media Data
• OOGAN: Disentangling GAN with One-Hot Sampling and Orthogonal Regularization
• Sketch-to-Art: Synthesizing Stylized Art Images From Sketches
• Using AI for Economic Upliftment of Handicraft Industry
• Improving image generative models with human interactions
• Developing Creative AI to Generate Sculptural Objects
• Off the Beaten Track: Using Deep Learning to Interpolate Between Music Genres
• Self-Supervised Sketch-to-Image Synthesis
• Autonomy, Authenticity, Authorship and Intention in computer generated art
• Camera Obscurer: Generative Art for Design Inspiration
• Hallucinating Point Cloud into 3D Sculptural Object
• Sym-parameterized Dynamic Inference for Mixed-Domain Image Translation
• Quality-aware Unpaired Image-to-Image Translation
• The societal and ethical relevance of computational creativity
• Ownership and Creativity in Generative Models
• Modeling and Forecasting Art Movements with CGANs
• Generative Adversarial Networks for Astronomical Images Generation
• Disentangling Action Sequences: Discovering Correlated Samples