Image style transfer is an emerging technique which is able to endow images with attractive artistic styles.
Transferring the style from one image onto another can be considered a problem of texture transfer. In texture transfer the goal is to synthesise a texture from a source image while constraining the texture synthesis in order to preserve the semantic content of a target image. There exists some non-parametric algorithms, but they are limited to inform the texture transfer with only low-level image features of the target image. Gatys et al introduced a way to use Convolutional Neural Network (CNN) to separate and recombine the image content and style of natural images by extracting image representations from response layers in VGG networks.
Later Johnson et al proposed a way to train a feed-forward network to approximate the operation. This technique was used by Prisma, an app that let users render any image with the chosen artistic style.
Currently, no events have been added to this timeline yet.
Be the first one to add some.
Documentaries, videos and podcasts
No infobox has been created on this topic. Be the first to add one.
- Machine learningA field of computer science enabling computers to learn.
- Convolutional neural networkA type of neural network which uses overlapping input neurons modeled on the behavior of human visual cortex. Convolutional neural networks are best known for their use in image analysis, specifically object recognition.
- Prisma (app)A photo-editing application