Follow

RT @m4rkmc@twitter.com

Samsung researchers have released a model that can generate faces in new poses from just a single image/frame (for each of face, pose). Done by building a well-trained landmark model in advance & one-shotting from that.

This gif is my favourite...
techcrunch.com/2019/05/22/mona

· Mastodon Twitter Crossposter · 5 · 53 · 38

@edvorg increasingly, what you see cannot be taken for granted...

@edvorg
En espérant qu'il reste une part du génie humain, comme ce cas limite remarquablement utilisé par Marcel Gotlib

@edvorg Ouais. Techniquement génial. Socialement flippant !!!

@edvorg
Did they use Hermine Granger as model for facial expressions?

@edvorg @winzstd holy shit! Trust no one. Anymore. Even if you see them. 🤦‍♂️ @rf

Sign in to participate in the conversation
Mastodon

Server run by the main developers of the project 🐘 It is not focused on any particular niche interest - everyone is welcome as long as you follow our code of conduct!