A State-of-the-Art Review on Image Synthesis with Generative Adversarial Networks
DOI:
https://doi.org/10.47672/ajce.1893Keywords:
Generative Adversarial Networks, Image Synthesis, Image-To-Image Translation, Image Editing, Cartoon GenerationAbstract
Purpose: The remarkable performance of Generative Adversarial Networks (GANs) in various applications has made them a popular subject in computer vision research, and they have also shown remarkable success in picture synthesis tasks.
Materials and Methods: Image processing, synthesis, generation, semantic editing, translation, super-resolution, inpainting, and cartoon creation are all areas covered in this article's presentation of the most recent GAN research. To demonstrate how they have improved the result, they analyze the methods used by these applications and describe them.
Findings: Insights into GAN research and a presentation of GAN-based applications in diverse contexts are the goals of this paper (Anon, 2022).
Implications to Theory, Practice and Policy: Following this, we will go over some of the difficulties encountered by GANs and provide solutions to these issues. We also discuss potential future areas of study for GANs, including video creation, 3D face reconstruction, and facial animation synthesis.
Downloads
References
Anon (2022). IEEE Xplore Full-Text PDF: [online] ieeexplore.ieee.org. Available at: https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=10372211 [Accessed 1 Mar. 2024].
Fan, J., Liu, T., Li, G., Chen, J., Shen, Y. and Du, X. (2020). Relational Data Synthesis using Generative Adversarial Networks: A Design Space Exploration. [online] arXiv.org. doi:https://doi.org/10.48550/arXiv.2008.12763.
Huang, H., Yu, P.S. and Wang, C. (2018). An Introduction to Image Synthesis with Generative Adversarial Nets. arXiv (Cornell University), 07(6). doi:https://doi.org/10.48550/arxiv.1803.04469.
Mao, Q., Lee, H.-Y., Tseng, H.-Y., Ma, S. and Yang, M.-H. (2019). Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis. [online] openaccess.thecvf.com. Available at: https://openaccess.thecvf.com/content_CVPR_2019/html/Mao_Mode_Seeking_Generative_Adversarial_Networks_for_Diverse_Image_Synthesis_CVPR_2019_paper.html [Accessed 1 Mar. 2024].
Pierrick Bourgeat (2022). Ea-GANs: Edge-Aware Generative Adversarial Networks for Cross-Modality MR Image Synthesis | IEEE Journals & Magazine | IEEE Xplore. [online] ieeexplore.ieee.org. Available at: https://ieeexplore.ieee.org/abstract/document/8629301/ [Accessed 1 Mar. 2024].
Qiao, Y., Chen, Q., Deng, C., Ding, N., Qi, Y., Tan, M., Ren, X. and Wu, Q. (2021). R-GAN: Exploring Human-like Way for Reasonable Text-to-Image Synthesis via Generative Adversarial Networks. https://dl.acm.org/doi/abs/10.1145/3474085.3475363(08). doi:https://doi.org/10.1145/3474085.3475363.
Shamsolmoali, P., Zareapoor, M., Granger, E., Zhou, H., Wang, R., Celebi, M.E. and Yang, J. (2021). Image synthesis with adversarial networks: A comprehensive survey and case studies. Information Fusion, [online] 72(09), pp.126-146. doi:https://doi.org/10.1016/j.inffus.2021.02.014.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Sai Mani Krishna Sistla , Suhas Jangoan, Ikram Ahamed Mohamed
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution (CC-BY) 4.0 License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
