A comprehensive review of image denoising in deep learning

• Main Authors: Jebur R.S., Zabil M.H.B.M., Hammood D.A., Cheng L.K.
• Other Authors: 57214077047
• Format: Article
• Published: Springer 2025
• Subjects: Deep learning; Gaussian noise (electronic); Learning systems; Blind denoising; Discriminative learning; Gaussians; Hybrid noisy image; Learning methods; Learning techniques; Noisy image; Optimization models; Salt-and-pepper noise; Salt and pepper noise

Deep learning has gained significant interest in image denoising, but there are notable distinctions in the types of deep learning methods used. Discriminative learning is suitable for handling Gaussian noise, while optimization models are effective in estimating real noise. However, there is limited research that summarizes the different deep learning techniques for image denoising. This paper conducts a comprehensive review of techniques and methods used for image denoising and identifying challenges associated with existing approaches. In this paper, a comparative study of deep techniques is offered in image denoising. The study conducted a comprehensive review of 68 papers on image denoising published between 2018 and 2023, providing a detailed analysis of the field?s progress and methodologies over a period of 5 years. Through its literature review, the paper provides a comprehensive summary of image denoising in deep learning, including machine learning methods for image denoising, CNNs for image denoising, additive white noisy-image denoising, real noisy image denoising, blind denoising, hybrid noisy images, state- of-the-art methods for image denoising with deep learning, salt and pepper noise, non-linear filters for digital color images. The main objective of this paper is to provide a comprehensive overview of various approaches used for image denoising, each of which has been explored and developed based on individual research studies. The paper aims to discuss these approaches in a systematic and organized manner, comparing their strengths and weaknesses to provide insights for future research in the field. ? The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023.