Image Quality Enhancement via Machine Learning: A Unified Approach to Super-Resolution, Denoising, and Low-Density Enhancement

Abstract

Problem: The escalating demand for high-quality images across various applications has underscored the necessity for advanced image enhancement techniques. Traditionally, denoising, super-resolution, and low-density enhancement, the three key image enhancement techniques, have been approached independently, resulting in separate developments for each. Unfortunately, a unified framework that seamlessly combines all three techniques and surpasses individual method performance has been lacking. Proposed Idea: The objective of this research is to develop a unified image enhancement framework that not only unites these techniques but also substantiates its superiority over existing individual methods through an extensive series of experiments. The proposed method utilizes cascade autoencoder architectures to generate high-quality enhanced images. In addition, an auxiliary artifact type prediction module has been introduced to enhance the noise-awareness, resulting in improved accuracy. Result: The proposed method demonstrates superior performance in achieving state-of-the-art accuracy when evaluated against three image quality metrics on various public datasets. Additionally, the practical application of the proposed method showcases its efficacy in effectively solving real-world problems.