Generation of believable fake eyes pictures.


In order to generate fake believable eyes images I've used a branch A.I called Machine Learning, more specifically I've used a GAN.

A generative adversarial network (GAN) is a class of machine learning systems invented by Ian Goodfellow and his colleagues in 2014. Two neural networks contest with each other in a game (in the sense of game theory, often but not always in the form of a zero-sum game). Given a training set, this technique learns to generate new data with the same statistics as the training set. For example, a GAN trained on photographs can generate new photographs that look at least superficially authentic to human observers, having many realistic characteristics. Though originally proposed as a form of generative model for unsupervised learning, GANs have also proven useful for semi-supervised learning,[2] fully supervised learning,[3] and reinforcement learning.[4] In a 2016 seminar, Yann LeCun described GANs as "the coolest idea in machine learning in the last twenty years".

Source : wikipedia

Below two videos that show the sequences of fake eyes generation, the left sequence is generated using only human eyes photos the right sequences is generated using a dataset of images that includes both human and animal eyes photos.

Gans explained-w230.jpg




  • w230studio FB
  • w30studio Instagram

Welcome to the W230 studio website. All rights reserved © 2020


Gans explained