From Probabilistic Models to Transformers: The Technological Trajectory of Generative AI in Vision Tasks

Chengcheng Dong

doi:10.54254/2755-2721/2025.LD27180

Applied and Computational EngineeringOpen access

From Probabilistic Models to Transformers: The Technological Trajectory of Generative AI in Vision Tasks

Research Article

Open Access

From Probabilistic Models to Transformers: The Technological Trajectory of Generative AI in Vision Tasks

Chengcheng Dong ^1*

¹ Computer science big data, University of Wollongong, Northfields Ave Wollongong, NSW 2522, Australia

^*Corresponding author: 127dcc@gmail.com

Published on 24 September 2025

ACE Vol.184

ISSN (Print): 2755-273X

ISSN (Online): 2755-2721

ISBN (Print): 978-1-80590-307-9

ISBN (Online): 978-1-80590-308-6

Download Cover

Abstract

With the rapid advancements in generative artificial intelligence (GAI), visual computing has witnessed transformative changes across a range of applications such as image synthesis, restoration, super-resolution, 3D reconstruction, and medical imaging. This review systematically examines the evolution of generative models, from early statistical approaches to state-of-the-art transformer-based architectures. Key models including variational autoencoders (VAE), generative adversarial networks (GAN), and diffusion models are compared in terms of their structure, training stability, image quality, and suitability for various visual tasks. In addition to technical progress, the review highlights the ethical, explainability, and safety challenges associated with GAI deployment, especially in high-stakes fields like healthcare and manufacturing. While GAI enables highly realistic and semantically meaningful image generation, challenges remain in balancing innovation with interpretability, computational efficiency, and social responsibility. The paper also acknowledges the limitations of static literature reviews in a rapidly evolving domain and calls for ongoing comparative studies and interdisciplinary collaboration to shape a responsible and sustainable future for generative AI in visual computing.

Keywords:

Generative AI, visual computing, diffusion models, image synthesis

View PDF

References

[1]. Generative AI accelerates homologation: FEV simplifies country-specific type approval processes. (2025). M2 Presswire.

[2]. Tasdelen, O., & Bodemer, D. (2025). Generative AI in the classroom: Effects of context-personalized learning material and tasks on motivation and performance. International Journal of Artificial Intelligence in Education, prepublish, 1–22.

[3]. Shabeeb, Z., Goyal, N., Nantogmah, A. P., & Lin, S. (2025). Learning the diffusion of nanoparticles in liquid phase TEM via physics-informed generative AI. Nature Communications, 16(1), 6298.

[4]. Wu, Z., Cao, L., & Qi, L. (2024). EVAE: Evolutionary variational autoencoder. IEEE Transactions on Neural Networks and Learning Systems, 36(2), 3288–3299.

[5]. BrightEdge Survey: Brands adapting to rise of AI-search and shift to generative engine optimization. (2025). Manufacturing Close-Up.

[6]. Yang, X., Liu, X., & Gao, Y. (2025). The impact of generative AI on students’ learning: A study of learning satisfaction, self-efficacy and learning outcomes. Educational Technology Research and Development, prepublish, 1–14.

[7]. Lee, C., Kim, J., Lim, S. J., & Zhang, Y. (2025). Generative AI risks and resilience: How users adapt to hallucination and privacy challenges. Telematics and Informatics Reports, 19, 100221.

[8]. Guha, P., Chen, S., Georges, A., & Dutta, A. (2025). Turning to Gen-AI as an empowerment tool for parents of teenage girls for conversations on online sexual harassment. AI & Society, prepublish, 1–13.

[9]. Rodger, D., Mann, P. S., Earp, B., & Zhu, X. (2025). Generative AI in healthcare education: How AI literacy gaps could compromise learning and patient safety. Nurse Education in Practice, 87, 104461.

[10]. Granić, A. (2025). Emerging drivers of adoption of generative AI technology in education: A review. Applied Sciences, 15(13), 6968.

[11]. Vinothkumar, S., Varadhaganapathy, S., Shanthakumari, R., Dhanushya, S., Guhan, S., & Krisvanth, P. (2024, June). Utilizing generative AI for text-to-image generation. In 2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT) (pp. 1–6). IEEE.

[12]. Croce, V., Caroti, G., De Luca, L., Piemonte, A., & Véron, P. (2023). Neural radiance fields (NeRF): Review and potential applications to digital cultural heritage. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 48, 453–460.

[13]. Koetzier, L. R., Wu, J., Mastrodicasa, D., Lutz, A., Chung, M., Koszek, W. A., ... & Willemink, M. J. (2024). Generating synthetic data for medical imaging. Radiology, 312(3), e232471.

References

[1]. Generative AI accelerates homologation: FEV simplifies country-specific type approval processes. (2025). M2 Presswire.

[3]. Shabeeb, Z., Goyal, N., Nantogmah, A. P., & Lin, S. (2025). Learning the diffusion of nanoparticles in liquid phase TEM via physics-informed generative AI. Nature Communications, 16(1), 6298.

[4]. Wu, Z., Cao, L., & Qi, L. (2024). EVAE: Evolutionary variational autoencoder. IEEE Transactions on Neural Networks and Learning Systems, 36(2), 3288–3299.

[5]. BrightEdge Survey: Brands adapting to rise of AI-search and shift to generative engine optimization. (2025). Manufacturing Close-Up.

[7]. Lee, C., Kim, J., Lim, S. J., & Zhang, Y. (2025). Generative AI risks and resilience: How users adapt to hallucination and privacy challenges. Telematics and Informatics Reports, 19, 100221.

[10]. Granić, A. (2025). Emerging drivers of adoption of generative AI technology in education: A review. Applied Sciences, 15(13), 6968.

[13]. Koetzier, L. R., Wu, J., Mastrodicasa, D., Lutz, A., Chung, M., Koszek, W. A., ... & Willemink, M. J. (2024). Generating synthetic data for medical imaging. Radiology, 312(3), e232471.

Cite this article

Dong,C. (2025). From Probabilistic Models to Transformers: The Technological Trajectory of Generative AI in Vision Tasks. Applied and Computational Engineering,184,24-29.

Data availability

The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.

About volume

Volume title: Proceedings of CONF-MLA 2025 Symposium: Intelligent Systems and Automation: AI Models, IoT, and Robotic Algorithms

ISBN: 978-1-80590-307-9(Print) / 978-1-80590-308-6(Online)

Editor: Hisham AbouGrad

Conference website: https://www.confmla.org/

Conference date: 17 November 2025

Series: Applied and Computational Engineering

Volume number: Vol.184

ISSN: 2755-2721(Print) / 2755-273X(Online)

© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license. Authors who publish this series agree to the following terms:

1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.

2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.

3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open access policy for details).