A Review on Generative AI For Text-To-Image and Image-To-Image Generation and Implications To Scientific Images
It provides a comparative analysis for researchers in AI and scientific imaging, but is incremental as a review paper.
This review surveys state-of-the-art generative AI methods for text-to-image and image-to-image generation, focusing on architectures like VAEs, GANs, and diffusion models, and discusses their implications for scientific images.
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.