A Survey of Modern Image Enhancement Techniques from Deep Learning to Diffusion Models

Niteen Vaghela , Vishal Patel , Jigar Dalvadi , Shruti Gami

Image Enhancement, Deep Learning, Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), Diffusion Models, Super-Resolution, Low-Light Enhancement.

Image enhancement is a fundamental area within computer vision and image processing, aimed at improving the perceptual quality and interpretability of images for human viewers and downstream computational tasks. While traditional methods have long relied on histogram manipulation and filter-based approaches, the field has been revolutionized by the advent of deep learning. This paper provides a comprehensive survey of the latest image enhancement methodologies. We begin with a brief overview of conventional techniques before delving into the dominant paradigm of deep learning, covering Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs). Furthermore, we explore the emerging and cutting-edge application of diffusion models, which have demonstrated remarkable capabilities in generating high-quality, perceptually superior images. The paper discusses the strengths, limitations, and typical applications of each methodological family, offering a clear perspective on the current state and future trajectory of image enhancement research.

Published Paper   E-Certificate

"A Survey of Modern Image Enhancement Techniques from Deep Learning to Diffusion Models", JNRID - JOURNAL OF NOVEL RESEARCH AND INNOVATIVE DEVELOPMENT (www.JNRID.org), ISSN:2984-8687, Vol.3, Issue 10, page no.a175-a179, October-2025, Available :https://tijer.org/JNRID/papers/JNRID2510020.pdf

Volume 3 Issue 10, October-2025

Pages : a175-a179

Paper Reg. ID: JNRID_701758

Published Paper Id: JNRID2510020

Downloads: 000217

Research Area: Science and Technology

Country: Anand, Gujarat, India

Published Paper PDF: https://tijer.org/JNRID/papers/JNRID2510020

Published Paper URL: https://tijer.org/JNRID/viewpaperforall?paper=JNRID2510020

ISSN: 2984-8687 | IMPACT FACTOR: 9.57 Calculated By Google Scholar | ESTD YEAR: 2023

An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.57 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator

Publisher: JNRID (IJ Publication) Janvi Wave

This work is licensed under a Creative Commons Attribution 4.0 International License and The Open Definition