Deep Generative Adversarial Networks for Image-to-Image Translation: A Review

Aziz Alotaibi

doi:10.3390/sym12101705

Abstract

Many image processing, computer graphics, and computer vision problems can be treated as image-to-image translation tasks. Such translation entails learning to map one visual representation of a given input to another representation. Image-to-image translation with generative adversarial networks (GANs) has been intensively studied and applied to various tasks, such as multimodal image-to-image translation, super-resolution translation, object transfiguration-related translation, etc. However, image-to-image translation techniques suffer from some problems, such as mode collapse, instability, and a lack of diversity. This article provides a comprehensive overview of image-to-image translation based on GAN algorithms and its variants. It also discusses and analyzes current state-of-the-art image-to-image translation techniques that are based on multimodal and multidomain representations. Finally, open issues and future research directions utilizing reinforcement learning and three-dimensional (3D) modal translation are summarized and discussed.

Highlights

IntroductionWith the rapid advancement in deep learning algorithms, the tasks of analyzing and understanding digital images for many computer vision applications have drawn increasing attention in the recent years due to such algorithms’ extraordinary performance and availability of large amounts of data
With the rapid advancement in deep learning algorithms, the tasks of analyzing and understanding digital images for many computer vision applications have drawn increasing attention in the recent years due to such algorithms’ extraordinary performance and availability of large amounts of data.Such algorithms directly process raw data and obviate the need for domain experts or handcrafted features [1,2,3]
Adam optimizer to train the model that achieves the state-of-the-art performance on class-condition image synthesis

Summary

Introduction

With the rapid advancement in deep learning algorithms, the tasks of analyzing and understanding digital images for many computer vision applications have drawn increasing attention in the recent years due to such algorithms’ extraordinary performance and availability of large amounts of data. Such algorithms directly process raw data (e.g., an RGB image) and obviate the need for domain experts or handcrafted features [1,2,3]. Such models are able to generate new samples by learning the estimation of the joint probability distribution p (x,y) and predicting y [14] in contexts, such as image super-resolution [15,16], text-to-image generation [17,18], and image-to-image translation [19,20]

Results

Discussion

Conclusion