The reviewed record of science sign in
Pith

arxiv: 2502.21151 · v2 · pith:5DFME4W2 · submitted 2025-02-28 · cs.CV

A Review on Generative AI For Text-To-Image and Image-To-Image Generation and Implications To Scientific Images

Reviewed by Pithpith:5DFME4W2open to challenge →

classification cs.CV
keywords generativegenerationimage-to-imagereviewscientifictext-to-imageadversarialanalysis
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. The critical slowing down in diffusion models

    cond-mat.dis-nn 2026-05 conditional novelty 8.0

    Diffusion models on the Gaussian O(n) model exhibit critical slowing down with shallow networks that deeper local score approximations can reduce to logarithmic training-time scaling.

  2. FaSTA$^*$: Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image Editing

    cs.CV 2025-06 unverdicted novelty 7.0

    FaSTA* combines LLM fast planning with A* search and inductive subroutine mining to create an efficient agent for multi-turn image editing tasks.

  3. The critical slowing down in diffusion models

    cond-mat.dis-nn 2026-05 unverdicted novelty 6.0

    Diffusion models suffer critical slowing down when sampling near criticality in the O(n) model but deeper local architectures reduce training-time scaling from quadratic to logarithmic in system size.