Skip to main content
EXTENDED SEARCH
Log in
Top
Published in:
Read chapter Read first chapter

2025 | OriginalPaper | Chapter

CLR-GAN: Improving GANs Stability and Quality via Consistent Latent Representation and Reconstruction

Authors : Shengke Sun, Ziqian Luan, Zhanshan Zhao, Shijie Luo, Shuzhen Han

Published in: Computer Vision – ECCV 2024

Publisher: Springer Nature Switzerland

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

The chapter 'CLR-GAN: Improving GANs Stability and Quality via Consistent Latent Representation and Reconstruction' introduces a novel method to enhance the stability and quality of Generative Adversarial Networks (GANs). It addresses the long-standing issue of training instability by rethinking the relationship between the generator and discriminator. The proposed method, CLR-GAN, introduces two additional learning objectives: latent consistency loss and reconstruction loss. These objectives aim to make the generator and discriminator more consistent, leading to a fairer and more stable training process. The chapter provides a detailed explanation of the method, including its theoretical foundation, implementation details, and extensive experimental results. The experiments demonstrate that CLR-GAN outperforms existing methods in terms of image generation quality and stability, making it a promising approach for improving GAN training.
AI Generated

This summary of the content was generated with the help of AI.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Business + Economics & Engineering + Technology"

Online-Abonnement

Springer Professional "Business + Economics & Engineering + Technology" gives you access to:

  • more than 102.000 books
  • more than 537 journals

from the following subject areas:

  • Automotive
  • Construction + Real Estate
  • Business IT + Informatics
  • Electrical Engineering + Electronics
  • Energy + Sustainability
  • Finance + Banking
  • Management + Leadership
  • Marketing + Sales
  • Mechanical Engineering + Materials
  • Insurance + Risk


Secure your knowledge advantage now!

inform now

Springer Professional "Engineering + Technology"

Online-Abonnement

Springer Professional "Engineering + Technology" gives you access to:

  • more than 67.000 books
  • more than 390 journals

from the following specialised fileds:

  • Automotive
  • Business IT + Informatics
  • Construction + Real Estate
  • Electrical Engineering + Electronics
  • Energy + Sustainability
  • Mechanical Engineering + Materials





 

Secure your knowledge advantage now!

inform now

Springer Professional "Business + Economics"

Online-Abonnement

Springer Professional "Business + Economics" gives you access to:

  • more than 67.000 books
  • more than 340 journals

from the following specialised fileds:

  • Construction + Real Estate
  • Business IT + Informatics
  • Finance + Banking
  • Management + Leadership
  • Marketing + Sales
  • Insurance + Risk



Secure your knowledge advantage now!

inform now
previous chapter Deblur e-NeRF: NeRF from Motion-Blurred Events under High-speed or Low-light Conditions
next chapter Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence
Appendix
This content is only visible if you are logged in and have the appropriate permissions.
Literature
This content is only visible if you are logged in and have the appropriate permissions.
Metadata
Title
CLR-GAN: Improving GANs Stability and Quality via Consistent Latent Representation and Reconstruction
Authors
Shengke Sun
Ziqian Luan
Zhanshan Zhao
Shijie Luo
Shuzhen Han
Copyright Year
2025
Book
Computer Vision – ECCV 2024

Print ISBN: 978-3-031-73231-7

Electronic ISBN: 978-3-031-73232-4

Copyright Year: 2025

DOI
https://doi.org/10.1007/978-3-031-73232-4_12

Premium Partner

    Image Credits