An Introduction to Image Synthesis with Generative Adversarial Nets

By He Huang, Philip S. Yu, Changhu Wang. 2018

200 citations recorded by the source corpus.

There has been a drastic growth of research in Generative Adversarial Nets (GANs) in the past few years. Proposed in 2014, GAN has been applied to various applications such as computer vision and natural language processing, and achieves impressive performance. Among the many applications of GAN, image synthesis is the most well-studied one, and research in this area has already demonstrated the great potential of using GAN in image synthesis. In this paper, we provide a taxonomy of methods used in image synthesis, review different models for text-to-image synthesis and image-to-image translation, and discuss some evaluation metrics as well as possible future research directions in image synthesis with GAN.

Subfields: Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Editing in Style: Uncovering the Local Semantics of GANs (2020, background): “For a thorough review of the GAN literature we refer the reader to recent surveys in [7, 13, 27].”
Media Forensics and DeepFakes: An Overview (2020, background): “To this end, autoencoders and generative adversarial networks allowed to develop successful solutions [34] especially for”
Interactive Image Generation Using Scene Graphs (2019, unknown): “Since the advent of Generative Adversarial Networks (GANs), there have been many efforts in this direction (Huang et al., 2018).”
Deepfake Video Detection Using Convolutional Vision Transformer (2021, background): “Image synthesis deals with generating unseen images from sample training examples [23].”
A survey on face data augmentation for the training of deep neural networks (2019, methodology): “In comparison with IS, FID is more robust to noise and more sensitive to intra-class mode collapse [53].”
Conditional WaveGAN (2018, unknown): “In his 2018 paper, He Huang et al. [11] talks more about the usage of GANs for image synthesis and various techniques in this ﬁelds.”
Perceptual Pyramid Adversarial Networks for Text-to-Image Synthesis (2019, background): “So StackGAN consists of two separated GANs, which is difﬁcult to train and unstable to evaluate (Huang, Yu, and Wang 2018).”
Applications of machine learning to diagnosis and treatment of neurodegenerative diseases (2020, background): “General adversarial neural networks enable such image manipulation and creation by learning the useful features of the training dataset and generating a new dataset based on the learnt features 201,202 .”
Deepfakes generation and detection: state-of-the-art, open challenges, countermeasures, and way forward (2021, background): “trend involves the synthesis of videos from scratch using autoencoders, or GAN, for different applications [30] and, more specifically, photorealistic human face generation based on any attribute [31-34].”