Applications of GAN-Based Extension Methods in Image Processing

DOI

10.2991/978-94-6239-648-7_25How to use a DOI?

Keywords

Adversarial Generative Networks; Image Style Transfer; Deep Learning

Abstract

In the era of rapid AI advancement, Generative Adversarial Networks (GANs) stand as one of the most disruptive innovations in deep learning, deeply integrated into every facet of human society. This paper focuses on the optimization pathways within the GAN technology system, systematically reviewing research progress on GAN-based improvement methods. It categorizes and analyzes these advancements across four dimensions: innovative loss function design, generator-discriminator architecture optimization, dynamic training strategy control, and functional module expansion and enhancement. By examining typical application scenarios, particularly in image processing, the paper explores practical implementation strategies. By establishing a three-tier classification framework-“core components, training mechanisms, and extended architectures”-this paper fills a gap in existing reviews regarding the systematic categorization of GAN improvement methods. It reveals the technical essence and applicability boundaries of different optimization strategies. The findings provide methodological guidance for researchers selecting suitable approaches or designing novel improvements tailored to specific application scenarios, offering theoretical support for the engineering implementation and performance breakthroughs of GAN technology.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Yang Ding
PY  - 2026
DA  - 2026/04/24
TI  - Applications of GAN-Based Extension Methods in Image Processing
BT  - Proceedings of the International Workshop on Advances in Deep Learning for Image Analysis and Computer Vision (IWADIC 2025)
PB  - Atlantis Press
SP  - 224
EP  - 232
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6239-648-7_25
DO  - 10.2991/978-94-6239-648-7_25
ID  - Ding2026
ER  -