Semantic Image Completion and Enhancement using GANs

TL;DR

This paper discusses the use of Generative Adversarial Networks (GANs) for semantic image completion and enhancement, focusing on recovering missing regions and improving image quality by removing noise and blur.

Contribution

It provides an overview of GAN architectures and their application to image completion and enhancement tasks, highlighting their effectiveness in high-level semantic inference.

Findings

GANs improve image completion quality

GAN-based methods effectively remove noise and blur

Enhanced images retain more semantic details

Abstract

Semantic inpainting or image completion alludes to the task of inferring arbitrary large missing regions in images based on image semantics. Since the prediction of image pixels requires an indication of high-level context, this makes it significantly tougher than image completion, which is often more concerned with correcting data corruption and removing entire objects from the input image. On the other hand, image enhancement attempts to eliminate unwanted noise and blur from the image, along with sustaining most of the image details. Efficient image completion and enhancement model should be able to recover the corrupted and masked regions in images and then refine the image further to increase the quality of the output image. Generative Adversarial Networks (GAN), have turned out to be helpful in picture completion tasks. In this chapter, we will discuss the underlying GAN architecture and how they can be used used for image completion tasks.