Another great paper from Samsung AI lab! et al. animate heads using only few shots of target person (or even 1 shot). Keypoints, adaptive instance norms and GANs, no 3D face modelling at all. ▶️ 📝
the Mona Lisa finally speaks to us!! great paper: #AI living #portraits
AI animates faces from a single or few images. Paper:
#CyberpunkisNow Another look at Few-Shot Adversarial Learning of Realistic Neural Talking Head Models as implemented by Samsung AI lab This technology can animate highly realistic heads using as little as one starter image. More information here
Few-Shot Adversarial Learning of Realistic Neural Talking Head Models pdf: abs:
While technically impressive, I'm freaked out by the AI living portraits. Paper here
wow ! animated heads using only few shots of target person
Few-Shot Adversarial Learning of Realistic Neural Talking Head Models Deep-fakes from one or two photos. See the YouTube clip for footage of it learning from historical photos and even a painting
I did some “digital art” in the 90ies, and thought image morphing was so cool. Thinking it’s getting pretty scary now.