Researchers have developed an AI system — InstaGAN — that can swap sheep with giraffes, skirts with pants, and more in images.
Swapping giraffe for sheep. Switching skirts with jeans. It might sound far-fetched, but those are just a few of the feats a machine learning algorithm designed by researchers at the Korea Advanced Institute of Science and Technology and the Pohang University of Science and Technology can accomplish after ingesting large datasets of images. It’s described in a new paper (“ InstaGAN: Instance-Aware Image-to-Image Translation “) published on the preprint server Arxiv.org this week.
Image-to-image translation systems — that is, systems which learn the mapping from input image to output image — aren’t anything new, to be clear. Only earlier this month, Google AI researchers developed a model that can realistically insert an object in a photo by predicting its scale, occlusions, pose, shape, and more. But as the creators of InstaGAN wrote in the paper, even state-of-the-art methods aren’t perfect.
“Unsupervised image-to-image translation has gained considerable attention due to the recent impressive progress based on generative adversarial networks (GANs),” they said.
