Interpreting Generative Adversarial Networks for Interactive Image Generation

08/10/2021
by   Bolei Zhou, et al.
7

Great progress has been made by the advances in Generative Adversarial Networks (GANs) for image generation. However, there lacks enough understanding on how a realistic image can be generated by the deep representations of GANs from a random vector. This chapter will give a summary of recent works on interpreting deep generative models. We will see how the human-understandable concepts that emerge in the learned representation can be identified and used for interactive image generation and editing.

READ FULL TEXT

page 2

page 3

page 5

page 6

research
05/31/2017

Megapixel Size Image Creation using Generative Adversarial Networks

Since its appearance, Generative Adversarial Networks (GANs) have receiv...
research
07/09/2021

Deep Image Synthesis from Intuitive User Input: A Review and Perspectives

In many applications of computer graphics, art and design, it is desirab...
research
04/03/2019

Constrained Generative Adversarial Networks for Interactive Image Generation

Generative Adversarial Networks (GANs) have received a great deal of att...
research
07/21/2022

A Survey on Leveraging Pre-trained Generative Adversarial Networks for Image Editing and Restoration

Generative adversarial networks (GANs) have drawn enormous attention due...
research
05/18/2021

Decorating Your Own Bedroom: Locally Controlling Image Generation with Generative Adversarial Networks

Generative Adversarial Networks (GANs) have made great success in synthe...
research
06/07/2019

Labeled Graph Generative Adversarial Networks

As a new way to train generative models, generative adversarial networks...
research
02/10/2020

Connecting GANs and MFGs

Generative Adversarial Networks (GANs), introduced in 2014 [12], have ce...

Please sign up or login with your details

Forgot password? Click here to reset