Comparing CNNs and GANs for Image Completion

Abstract

Imperfections or defects inevitably occur in images due to inexperienced photographers, inadequate methods of preservation, or even some deliberate hacking. Image restoration or completion has been performed using various manual methods in the past, be it being drawn by artists based on their creativity or deleting noise and blur effects using software like Photoshop. On a large scale, manual image completion is infeasible and has quite a lot of limitations. Modern advancements in Computer Vision and Deep Learning have allowed man to automate such tasks with high efficiency. Manual restoration usually relies on prior experience in the subject and sometimes even creativity to reconstruct the image based on the artist's imagination. At the same time, deep learning produces excellent results given enough training data. Deep learning methods can improvise and generalize better too and hence outperform the traditional manual methods. In this project, image completion is performed using 2 Deep Learning models - Convolutional Neural Networks(CNN) and Generative Adversarial Networks(GAN). Adversarial Networks have been proven to be very handy in image to image translation tasks and image reconstruction and hence this is explored widely. Both Deep Convolutional GANs as well as Conditional GANs are used for this task and their respective performances are compared for the above task.