In order to create a personalized talking head model, these works require training on a large dataset of images of a single person.
Despite recent progress in generative image modeling, successfully generating high-resolution, diverse samples from complex datasets such as ImageNet remains an elusive goal.
Ranked #1 on Image Generation on CIFAR-10 (NFE metric)
Conditional Image Generation Vocal Bursts Intensity Prediction
Gatys et al. recently introduced a neural algorithm that renders a content image in the style of another image, achieving so-called style transfer.