Enregistré dans:
Détails bibliographiques
Auteurs principaux: Sordo, Zineb, Chagnon, Eric, Ushizima, Daniela
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2502.21151
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929752446599168
author Sordo, Zineb
Chagnon, Eric
Ushizima, Daniela
author_facet Sordo, Zineb
Chagnon, Eric
Ushizima, Daniela
contents This review surveys the state-of-the-art in text-to-image and image-to-image generation within the scope of generative AI. We provide a comparative analysis of three prominent architectures: Variational Autoencoders, Generative Adversarial Networks and Diffusion Models. For each, we elucidate core concepts, architectural innovations, and practical strengths and limitations, particularly for scientific image understanding. Finally, we discuss critical open challenges and potential future research directions in this rapidly evolving field.
format Preprint
id arxiv_https___arxiv_org_abs_2502_21151
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Review on Generative AI For Text-To-Image and Image-To-Image Generation and Implications To Scientific Images
Sordo, Zineb
Chagnon, Eric
Ushizima, Daniela
Computer Vision and Pattern Recognition
This review surveys the state-of-the-art in text-to-image and image-to-image generation within the scope of generative AI. We provide a comparative analysis of three prominent architectures: Variational Autoencoders, Generative Adversarial Networks and Diffusion Models. For each, we elucidate core concepts, architectural innovations, and practical strengths and limitations, particularly for scientific image understanding. Finally, we discuss critical open challenges and potential future research directions in this rapidly evolving field.
title A Review on Generative AI For Text-To-Image and Image-To-Image Generation and Implications To Scientific Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.21151