In fine art, especially painting, humans have mastered the skill to createunique visual experiences through composing a complex interplay between thecontent and style of an image. Thus far the algorithmic basis of this processis unknown and there exists no artificial system with similar capabilities.However, in other key areas of visual perception such as object and facerecognition near-human performance was recently demonstrated by a class ofbiologically inspired vision models called Deep Neural Networks. Here weintroduce an artificial system based on a Deep Neural Network that createsartistic images of high perceptual quality. The system uses neuralrepresentations to separate and recombine content and style of arbitraryimages, providing a neural algorithm for the creation of artistic images.Moreover, in light of the striking similarities between performance-optimisedartificial neural networks and biological vision, our work offers a pathforward to an algorithmic understanding of how humans create and perceiveartistic imagery.
展开▼
