Image Style Transfer Using Convolutional Neural Networks¶
Why this mattered¶
TBD
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.
Related¶
- cite → ImageNet Large Scale Visual Recognition Challenge — Neural style transfer uses CNN feature representations from networks trained on ImageNet, whose benchmark was standardized by the ILSVRC dataset and challenge.
- cite → ImageNet classification with deep convolutional neural networks — Neural style transfer relies on the hierarchical convolutional features popularized by AlexNet-style ImageNet classifiers to separate content and texture statistics.
- cite ← Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network — SRGAN adopts a perceptual loss based on deep feature activations, a strategy popularized by neural style transfer.
- cite ← Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks — CycleGAN related its unpaired domain translation objective to neural style transfer's use of convolutional features to change image appearance.