Golden
LoginSign Up
Image Style Transfer

Image Style Transfer

A technique that endow images with selected artistic styles.

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.

Timeline

People

Name
Role
Related Golden topics

Further reading

Title
Author
Link
Type

Documentaries, videos and podcasts

Title
Date
Link

Companies

Company
CEO
Location
Products/Services

References