Translate

lunedì 14 dicembre 2015

# s-ai: Tom "persona" 3D revisited ...

<< Imagine being able to have a conversation with anyone you can’t actually get to meet in person (..) and interact with them >>

<< it’s possible for machine learning algorithms to capture the “persona” and create a digital model of a well-photographed person like Tom Hanks from the vast number of images of them available on the Internet. With enough visual data to mine, the algorithms can also animate the digital model of Tom Hanks to deliver speeches that the real actor never performed >>

http://www.kurzweilai.net/how-to-animate-a-digital-model-of-a-person-from-images-collected-from-the-internet

http://grail.cs.washington.edu/projects/3DPersona/

https://homes.cs.washington.edu/~supasorn/0550.pdf

International Conference on Computer Vision (ICCV), 2015

http://pamitc.org/iccv15/

Nessun commento:

Posta un commento