Image Transformation with a Hybrid Autoencoder and Generative Adversarial Network Machine Learning Architecture

摘要

An encoder artificial neural network (ANN) may be configured to receive an input image patch and produce a feature vector therefrom. The encoder ANN may have been trained with a first plurality of domain training images such that an output image patch visually resembling the input image patch can be generated from the feature vector. A generator ANN may be configured to receive the feature vector and produce a generated image patch from the first feature vector. The generator ANN may have been trained with feature vectors derived from a first plurality of domain training images and a second plurality of generative training images such that the generated image patch visually resembles the input image patch but is constructed of a newly-generated image elements visually resembling one or more image patches from the second plurality of generative training images.