Image-to-Image Translation

Jump to: navigation, search

YouTube search... ...Google search

Image-to-image translation is the controlled conversion of a given source image to a target image. Examples might be the conversion of day image to night image, or black and white photographs to color photographs.


  • Paired
  • Unparied



Existing image to image translation approaches have limited scalability and robustness in handling more than two domains, since different models should be built independently for every pair of image domains. StarGAN is a novel and scalable approach that can perform image-to-image translations for multiple domains using only a single model. Image-to-Image Translation | Yongfu Hao



An approach for learning to translate an image from a source domain X to a target domain Y in the absence of paired examples Image-to-Image Translation | Yongfu Hao


pix2pix GAN

tUNIT: Truly Unsupervised Image-to-Image Translation

dUNIT: Detection-Based Unsupervised Image-to-Image Translation

fUNIT: Few-Shot Unsupervised Image-to-Image Translation

Unsupervised image-to-image translation methods learn to map images in a given class to an analogous image in a different class, drawing on unstructured (non-registered) datasets of images.


UNIT: UNsupervised Image-to-image Translation