Samsung AI lab develops tech that can animate highly realistic heads using only a few - or in some cases - only one starter image.
Paper: https://arxiv.org/abs/1905.08233 “Several recent works have shown how highly realistic human head images (videos) can be obtained by training convolutional neural networks to generate them. In order to create a personalized talking head model, these works require training on a large dataset of images of a single person. However, in many practical scenarios, such personalized talking head models need to be learned from a few image views of a person, potentially even a single image. Here, we present a system with such few-shot capability .. (snip) YouTube Examples: https://www.youtube.com/watch?v=p1b5aiTrGzY&feature=youtu.be Seems to me this may be a turning point in terms of human truth. Regards Stephen _______________________________________________ Link mailing list Link@mailman.anu.edu.au http://mailman.anu.edu.au/mailman/listinfo/link
