Due to the profundity of the concept of artistic style the optimal solution for style transfer is ill-defined. The variety of approaches that have been proposed represent partial solutions to varying degrees of efficiency, usability and quality of results. In this work a photo-realistic style transfer method for image and video based on vision science principles and on a recent mathematical formulation for the deterministic decoupling of features is proposed. As a proxy for mimicking the effects of camera color rendering or post processing, the employed features (the first through fourth order moments of the color distribution) represent important cues for visual adaptation and pre-attentive processing.
The method is evaluated on the above criteria in a series of application relevant experiments and is shown to have results of high visual quality, without spatio-temporal artifacts and validation tests in the form of observer preference experiments show that it compared very well with the state-of-the-art. The computational complexity of the algorithm is low, and a numerical implementation that is amenable for motion picture production is proposed and demonstrated. Finally, general recommendations for photo-realistic style transfer in context of the popular avenues of study (deep learning, optimal transport, etc.) are discussed.
Trevor Canham is studying color imaging under the supervision of Michael Brown at York University in Toronto. He recieved a BSc in Motion Picture Science from the Rochester Institute of Technology and spent several years working in Marcelo Bertalmío's Image Processing for Enhanced Cinematography lab in Barcelona. His interests lie in the interaction between color phenomenology and imaging systems.