Image Style Transfer Using Convolutional Neural Networks

TLDR

Rendering semantic content in different styles is difficult, largely because prior methods lack representations that separate content from style. The study introduces a neural algorithm of artistic style that separates and recombines image content and style. By employing CNN‑derived representations optimized for object recognition, the algorithm explicitly encodes high‑level image information, enabling the synthesis of high‑perceptual‑quality images that blend a photograph’s content with the appearance of well‑known artworks. The results provide insights into CNN‑learned representations and demonstrate their potential for high‑level image synthesis and manipulation.

Abstract

Rendering the semantic content of an image in different styles is a difficult image processing task. Arguably, a major limiting factor for previous approaches has been the lack of image representations that explicitly represent semantic information and, thus, allow to separate image content from style. Here we use image representations derived from Convolutional Neural Networks optimised for object recognition, which make high level image information explicit. We introduce A Neural Algorithm of Artistic Style that can separate and recombine the image content and style of natural images. The algorithm allows us to produce new images of high perceptual quality that combine the content of an arbitrary photograph with the appearance of numerous wellknown artworks. Our results provide new insights into the deep image representations learned by Convolutional Neural Networks and demonstrate their potential for high level image synthesis and manipulation.