Advanced Image Generation using Generative Adversarial Networks (GANs): Innovations in Creating High-Quality Synthetic Images with AI
Authors:
- 19 March 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1414-1418
Abstract
This research analysis reviews the latest developments in advanced Generative Adversarial Networks (GANs) picture synthesis with focus on enhancements aimed to create high-quality synthetic images. The goal of this work is to expand the limits of image generation and quality by using the capacity of GANs, particularly by performing basic functions such as Input, Conv2D, Dense, Flatten, and Dropout. This study consists of creating and improving a GAN model capable of generating realistic and elaborate graphics in different areas. If the high level results were encouraging, the results were even better once a Flask based user interface is added. This user interface allows for the generation and real-time visualization of artificial images, thus providing a useful environment to test and evaluate the effectiveness of the GAN model. The findings of this study contribute to the field of artificial intelligence applications by offering a robust approach to generating images that can be utilized for diverse applications, such as data augmentation, simulations, and entertainment. This paper lays out the methods employed, challenges embraced, and success achieved indicating the capacity of GANs to raise picture synthesis to the next level.Keywords
This publication has 12 references indexed in Scilit:
- Will sentiment analysis need subculture? A new data augmentation approachJournal of the Association for Information Science and Technology, 2024
- Creating a Protected Virtual Learning Space: A Comprehensive Strategy for Security and User Experience in Online Education2024
- Text to Image Generation with Semantic-Spatial Aware GAN2022
- StyleSwin: Transformer-based GAN for High-resolution Image Generation2022
- Image Generation Using GAN and Its Classification Using SVM and CNN2021
- A State-of-the-Art Review on Image Synthesis With Generative Adversarial NetworksIEEE Access, 2020
- Comparison of Objective Image Quality Metrics to Expert Radiologists’ Scoring of Diagnostic Quality of MR ImagesIEEE Transactions on Medical Imaging, 2019
- Image Generation from Sketch Constraint Using Contextual GAN2018
- GAN-based synthetic brain MR image generation2018
- Generative adversarial networks: introduction and outlookIEEE/CAA Journal of Automatica Sinica, 2017