CariGAN: Stanford graduate student Kaidi Cao will join fellow AI researchers Jing Liao of the City University of Hong Kong and Lu Yuan of Microsoft in SIGGRAPH Asia To be held at Tokio in December, to present an incredible neural network that draws caricatures.
This particular AI, actually consists of two generative adversarial networks (GAN), and is called CariGAN. The first of its neural networks, CariGeoGAN, determines the geometry of a face in a photograph and renders it as a caricature. CariStyGAN, the other half of CariGAN, does the “style transfer” or applies the artistic look to the design.
To empower CariGAN with the ability to turn a boring photo into a very pleasing design, the system was trained on thousands of pictures created by human hands.
To determine the effectiveness of the machine, the researchers conducted two studies. The first was to ensure that the AI caricatures retained the identity of the portrait. and the second study to determine the overall effectiveness of the "design" compared to human parts.
Both surveys seem to have been quite successful:
CariGANs AI can also analyze the frames from one video and create caricatures. The images below are created from the frames of a video of President Trump speaking.
Images from TNW
________________________
- BGP hijack on Google from a Nigerian ISP
- Qualcomm QTM052 mmWave smaller antennas 5G
- Pagespeed Insights with Lighthouse: what's new technology
- Fake News Using AI: When the CIA leaves behind the spies