Article 4FTEE Samsung AI Machine Learning Turns Mona Lisa and Other Famous Portraits Into Realistic Talking Heads

Samsung AI Machine Learning Turns Mona Lisa and Other Famous Portraits Into Realistic Talking Heads

by
Lori Dorn
from Laughing Squid on (#4FTEE)
Talking-Mona-Lisa-AI.png

Mona-Lisa-Talking.gif?w=640

Researchers at the Samsung AI Center in Moscow, Russia have quite amazingly turned Mona Lisa and other famous subjects of photos and art into realistic talking heads. This "Few-Shot Adversarial Learning" technology combs through thousands of videos and catalogs visual information. When an image is presented, the matching landmark features are located and put to work. Such examples include The Mona Lisa, Albert Einstein, and Salvador Dali. The results are spooky, to say the least.

We present a system for learning full-body neural avatars, i.e. deep networks that produce full-body renderings of a person for varying body pose and camera position. Our system takes the middle path between the classical graphics pipeline and the recent deep learning approaches that generate images of humans using image-to-image translation.

Albert-Einstein-Talking.gif?w=640

Salvador-Dali-Talking.gif?w=640

via PetaPixel

Related Laughing Squid Posts

NVIDIA Demonstrates New AI Technology for Reconstructing Photos With Realistic Results

A Deep Learning System That Removes Visual Noise From Digital Images by Looking at Pixelated Photos

How a High Profile Theft and an Enthusiastic Critic Made the Mona Lisa So Famous

Follow Laughing Squid on Facebook, Twitter, Flipboard and Subscribe by Email.

The post Samsung AI Machine Learning Turns Mona Lisa and Other Famous Portraits Into Realistic Talking Heads first appeared on Laughing Squid.

External Content
Source RSS or Atom Feed
Feed Location http://laughingsquid.com/feed/
Feed Title Laughing Squid
Feed Link https://laughingsquid.com/
Reply 0 comments