Generating new plausible samples was the application described in the original paper by Ian Goodfellow, et al. in the 2014 paper “Generative Adversarial Networks” where GANs were used to generate new plausible examples for the MNIST handwritten digit dataset, the CIFAR-10 small object photograph dataset, and the Toronto Face Database.
Examples of GANs used to Generate New Plausible Examples for Image Datasets.Taken from Generative Adversarial Nets, 2014.
This was also the demonstration used in the important 2015 paper titled “Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks” by Alec Radford, et al. called DCGAN that demonstrated how to train stable GANs at scale. They demonstrated models for generating new examples of bedrooms.
Example of GAN-Generated Photographs of Bedrooms.Taken from Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks, 2015.
Importantly, in this paper, they also demonstrated the ability to perform vector arithmetic with the input to the GANs (in the latent space) both with generated bedrooms and with generated faces.
Example of Vector Arithmetic for GAN-Generated Faces.Taken from Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks, 2015.
Tero Karras, et al. in their 2017 paper titled “Progressive Growing of GANs for Improved Quality, Stability, and Variation” demonstrate the generation of plausible realistic photographs of human faces. They are so real looking, in fact, that it is fair to call the result remarkable. As such, the results received a lot of media attention. The face generations were trained on celebrity examples, meaning that there are elements of existing celebrities in the generated faces, making them seem familiar, but not quite.
Examples of Photorealistic GAN-Generated Faces.Taken from Progressive Growing of GANs for Improved Quality, Stability, and Variation, 2017.
Their methods were also used to demonstrate the generation of objects and scenes.
Example of Photorealistic GAN-Generated Objects and ScenesTaken from Progressive Growing of GANs for Improved Quality, Stability, and Variation, 2017.
Examples from this paper were used in a 2018 report titled “The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation” to demonstrate the rapid progress of GANs from 2014 to 2017 (found via this tweet by Ian Goodfellow).
Example of the Progression in the Capabilities of GANs from 2014 to 2017.Taken from The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation, 2018.
Take my free 7-day email crash course now (with sample code).
Click to sign-up and also get a free PDF Ebook version of the course.
Download Your FREE Mini-Course
Andrew Brock, et al. in their 2018 paper titled “Large Scale GAN Training for High Fidelity Natural Image Synthesis” demonstrate the generation of synthetic photographs with their technique BigGAN that are practically indistinguishable from real photographs.
Example of Realistic Synthetic Photographs Generated with BigGANTaken from Large Scale GAN Training for High Fidelity Natural Image Synthesis, 2018.
Yanghua Jin, et al. in their 2017 paper titled “Towards the Automatic Anime Characters Creation with Generative Adversarial Networks” demonstrate the training and use of a GAN for generating faces of anime characters (i.e. Japanese comic book characters).
Example of GAN-Generated Anime Character Faces.Taken from Towards the Automatic Anime Characters Creation with Generative Adversarial Networks, 2017.
Inspired by the anime examples, a number of people have tried to generate Pokemon characters, such as the pokeGAN project and the Generate Pokemon with DCGAN project, with limited success.
Example of GAN-Generated Pokemon Characters.Taken from the pokeGAN project.
This is a bit of a catch-all task, for those papers that present GANs that can do many image translation tasks.
Phillip Isola, et al. in their 2016 paper titled “Image-to-Image Translation with Conditional Adversarial Networks” demonstrate GANs, specifically their pix2pix approach for many image-to-image translation tasks.
Examples include translation tasks such as:
Example of Photographs of Daytime Cityscapes to Nighttime With pix2pix.Taken from Image-to-Image Translation with Conditional Adversarial Networks, 2016.
Example of Sketches to Color Photographs With pix2pix.Taken from Image-to-Image Translation with Conditional Adversarial Networks, 2016.
Jun-Yan Zhu in their 2017 paper titled “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks” introduce their famous CycleGAN and a suite of very impressive image-to-image translation examples.
The example below demonstrates four image translation cases:
Example of Four Image-to-Image Translations Performed With CycleGANTaken from Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks, 2017.
The paper also provides many other examples, such as:
Example of Translation from Paintings to Photographs With CycleGAN.Taken from Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks, 2017.
We build amazing solutions for different industries including in the financial, government and telecommunication sectors.
