The company behind the impressive graphics cards have pulled off yet another machine learning-powered wizardry. Researchers from the Santa Clara-based chipmaker have created a new AI model — dubbed Ganimal — that can take in a picture of an animal and recreate its facial expression and pose on the face of any other creature. In a paper — titled “Few-Shot Unsupervised Image-to-Image Translation” aka FUNIT — the image-to-image translation method leverages generative adversarial networks (GANs), a neural network that has been widely adopted in a variety of image generation and transfer scenarios. You can give the tool a spin right here…
This story continues at The Next Web
from The Next Web https://ift.tt/2BL1cke
Comments
Post a Comment