Image-to-image is a system for creating digital images that resemble photographs based on a sketch drawn by a human artist. The user draws a line drawing of a particular object, either a facade, handbag, shoe or cat, and the system converts the drawing into a photorealistic image.
Image-to-image ‘works by training on pairs of images such as building facades… and then attempts to generate the corresponding output image from any input image you give it.’
HD, CB, HF, CF, HF, CFF
Isola, P., Zhu, J. Y., Zhou, T., & Efros, A. A. (2016). Image-to-image translation with conditional adversarial networks. arXiv preprint arXiv:1611.07004.