Generated Image

Capabilities
OpenAI’s fiction-spewing AI is learning to generate images | Karen Hao - MIT Technology Review By training GPT-2 on pixels instead of words, the model can accept half an image and predict how to complete it
- Generative Pre-trained Transformer (GPT)
Generative Visual Manipulation on the Natural Image Manifold - interactiveGAN (iGAN) | J. Zhu, P. Krähenbühl, E. Shechtman, and A. Efros
How deep learning fakes videos (Deepfakes) and how to detect it? | Jonathan Hui - Medium
Autoencoder (AE) / Encoder-Decoder
- Variational Autoencoder (VAE)
Generative Adversarial Network (GAN)
- Semi-Supervised Learning with Generative Adversarial Network (SSL-GAN)
- Context-Conditional Generative Adversarial Network (CC-GAN)
Point Cloud
Screening; Passenger, Luggage, & Cargo
Integrity Forensics

Generative Adversarial Network (GAN) employs two dueling neural networks to train a computer to learn the nature of a data set well enough to generate convincing fakes. When applied to images, this provides a way to generate often highly realistic fakery. In the most recent work, the researchers took inspiration from a technique known as Style Transfer to built their GAN in a fundamentally different way. This allowed their algorithm to identify different elements of a face, which the researchers could then control. These incredibly realistic fake faces show how algorithms can now mess with us | Will Knight - MIT Technology Review

To rework a famous saying, a fake picture is worth a thousand fake words, and with the increasing democratization of this kind of technology its going to become harder and harder to trust what we see on the web. As Joshua Rothman notes in the New Yorker, that presents a double-edge sword—not only will people be able to create forgeries to twist the public discourse, public figures will also have plausible deniability for anything they’re caught doing on camera. Nvidia’s Fake Faces Are a Masterpiece—But Have Deeper Implications | Edd Gent - SingularityHub