Image Denoising in the Deep Learning Era

Abstract

Over the last decade, the number of digital images captured per day witnessed a massive explosion. Nevertheless, the visual quality of photographs is often degraded by noise during image acquisition or transmission. With the re-emergence of deep neural networks, the performance of image denoising techniques has been substantially improved in recent years. The objective of this paper is to provide a comprehensive survey of recent advances in image denoising techniques based on deep neural networks. In doing so, we commence with a thorough description of the fundamental preliminaries of the image denoising problem followed by highlighting the benchmark datasets and the widely used metrics for objective assessments. Subsequently, we study the existing deep denoisers in the supervised and unsupervised categories and review the technical specifics of some representative methods within each category. Last but not least, we conclude the analysis by remarking on trends and challenges in the development of better state-of-the-art algorithms and future research.

Image Noise Removal in Ultrasound Breast Images Based on Hybrid Deep Learning Technique

“…As can be observed in Figure 6 , the BPI values of the denoised ultrasound images processed using the proposed technique were all high and far above the experimental threshold of 0.45. For denoised ultrasound images, the methods of Saeed Izadi et al (2022) [ 6 ], Thayammal et al (2021) [ 5 ], and Sujeet More et al (2021) [ 8 ] achieve BPI values of 0.40–0.45. For ultrasound images, the Nguyen Thanh-Trung et al (2021) [ 11 ] method has a lower BPI, with a maximum value of just 0.33, while the Dihan Zheng et al (2021) [ 14 ] algorithm consistently has a BPI below 0.2.…”

“… Graphical view of image noise removal comparison chart of proposed and state-of-art methods [ 5 , 6 , 8 , 9 , 11 , 14 ]. …”

“…In several applications, including image restoration, eye tracking, image registration, segmentation techniques, and image classification, recovering the actual image content is critical for good performance. While various methods have been developed for image noise removal, image noise reduction remains difficult, particularly when images are collected under poor conditions with excessive noise [ 6 ].…”

Accelerometer signals denoising without clean training data based on Noise2Noise approach

“…Neural networks, unlike traditional algorithms, can automatically learn features from signals and adaptively adjust model parameters, making them more suitable for handling complex and dynamic signals in real-world settings [20], [21]. In [12], variants of GRU, LSTM, and RNN neural networks are used for denoising accelerometer signals, achieving better results compared to traditional methods.…”

Self-Supervised Focus Measure Fusing for Depth Estimation from Computer-Generated Holograms

“…Inspired by the latest breakthroughs in selfsupervised image denoising [6][7][8][9][10], we propose in this paper an enhanced version of the automatic switch process which determines the appropriate depth value using both local and global information. The method involves extracting multiple depth maps from a reconstruction volume using various focus measures and patch sizes, then training a neural network in a selfsupervised manner to identify the depth map with the lowest average deviation.…”