Bibliographic Details
| Title: |
A SURVEY ON IMAGE GENERATION TECHNIQUES: PARADIGMS, EVOLUTION, DEEP LEARNING ADVANCEMENTS AND FUTURE DIRECTIONS. |
| Authors: |
Shah, Nrupesh1 nrupesh_shah@gecg28.ac.in, Patel, Sanjay2 sp_patel1@gtu.edu.in |
| Source: |
Reliability: Theory & Applications. Dec2025, Vol. 20 Issue 4, p82-104. 23p. |
| Subjects: |
Generative adversarial networks, Stable Diffusion, Deep learning, Technological innovations, Latent variables |
| Abstract: |
Image generation techniques have witnessed significant advancements in recent years. Classification of Image Generation Approaches is an important topic in today's rapidly advancing technological landscape. We will examine primary approaches in this field: Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), Stable Diffusion Processes (SDPs) and other similar approaches. GANs, VAEs and SDPs have shown remarkable performance in terms of image quality, as well as scalability and efficiency. This survey focuses onto seminal works that have shaped the field of image generation, spanning Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), Autoregressive Models, Flow based image generation as well as diffusion-based approaches, and also compares various evaluation metrices in the field. We also provide a list of challenges in this field. [ABSTRACT FROM AUTHOR] |
|
Copyright of Reliability: Theory & Applications is the property of International Group on Reliability and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Database: |
Engineering Source |
