Multimodal Unsupervised Image-To-Image Translation
13 papers with code • 6 benchmarks • 4 datasets
Multimodal unsupervised image-to-image translation is the task of producing multiple translations to one domain from a single image in another domain.
( Image credit: MUNIT: Multimodal UNsupervised Image-to-image Translation )
Image-to-image translation is a class of vision and graphics problems where the goal is to learn the mapping between an input image and an output image using a training set of aligned image pairs.
To translate an image to another domain, we recombine its content code with a random style code sampled from the style space of the target domain.
A good image-to-image translation model should learn a mapping between different visual domains while satisfying the following properties: 1) diversity of generated images and 2) scalability over multiple domains.
Our model takes the encoded content features extracted from a given input and the attribute vectors sampled from the attribute space to produce diverse outputs at test time.
In unsupervised image-to-image translation, the goal is to learn the mapping between an input image and an output image using a set of unpaired training images.