A Neural Algorithm of Artistic StyleLeon A. Gatys,1,2,3⇤ Alexander S. Ecker,1,2,4,5 Matthias Bethge1,2,41Werner Reichardt Centre for Integrative Neuroscienceand Institute of Theoretical Physics, University of T¨ubingen,Germany2Bernstein Center for Computational Neuroscience, T¨ubingen,Germany3Graduate School for Neural Information Processing, T¨ubingen,Germany4Max Planck Institute for Biological Cybernetics, T¨ubingen,Germany5Department of Neuroscience, Baylor College of Medicine, Houston, TX, USA⇤To whom correspondenceshould be addressed;E-mail: leon.gatys@bethgelab.orgIn fine art, especially painting, humans have mastered the skill to create uniquevisual experiences through composing a complex interplay between the con-tent and style of an image. Thus far the algorithmic basis of this process isunknown and there exists no artificial system with similar capabilities. How-ever, in other key areas of visual perception such as object and face recognitionnear-human performance was recently demonstrated by a class of biologicallyinspired vision models called Deep Neural Networks.1,2 Here we introduce anartificial system based on a Deep Neural Network that creates artistic imagesof high perceptual quality. The system uses neural representations to sepa-rate and recombine content and style of arbitrary images, providing a neuralalgorithm for the creation of artistic images. Moreover, in light of the strik-ing similarities between performance-optimised artificial neural networks andbiological vision,3–7 our work offers a path forward to an algorithmic under-standing of how humans create and perceive artistic imagery.1arXiv:1508.06576v2 [cs.CV] 2 Sep 2015The class of Deep Neural Networks that are most powerful in image processing tasks arecalled C...
