Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Unleashing the Power of Self-Supervised Image Denoising: A Comprehensive Review

Dan Zhang, Fangfang Zhou, Felix Albu, Yuanzhou Wei, Xiao Yang, Yuan Gu, Qiang Li

TL;DR

This comprehensive review thoroughly analyzes the latest advancements in self-supervised image denoising approaches, categorizing them into three distinct classes: General methods, Blind Spot Network (BSN)-based methods, and Transformer-based methods.

Abstract

The advent of deep learning has brought a revolutionary transformation to image denoising techniques. However, the persistent challenge of acquiring noise-clean pairs for supervised methods in real-world scenarios remains formidable, necessitating the exploration of more practical self-supervised image denoising. This paper focuses on self-supervised image denoising methods that offer effective solutions to address this challenge. Our comprehensive review thoroughly analyzes the latest advancements in self-supervised image denoising approaches, categorizing them into three distinct classes: General methods, Blind Spot Network (BSN)-based methods, and Transformer-based methods. For each class, we provide a concise theoretical analysis along with their practical applications. To assess the effectiveness of these methods, we present both quantitative and qualitative experimental results on various datasets, utilizing classical algorithms as benchmarks. Additionally, we critically discuss the current limitations of these methods and propose promising directions for future research. By offering a detailed overview of recent developments in self-supervised image denoising, this review serves as an invaluable resource for researchers and practitioners in the field, facilitating a deeper understanding of this emerging domain and inspiring further advancements.

Unleashing the Power of Self-Supervised Image Denoising: A Comprehensive Review

TL;DR

This comprehensive review thoroughly analyzes the latest advancements in self-supervised image denoising approaches, categorizing them into three distinct classes: General methods, Blind Spot Network (BSN)-based methods, and Transformer-based methods.

Abstract

The advent of deep learning has brought a revolutionary transformation to image denoising techniques. However, the persistent challenge of acquiring noise-clean pairs for supervised methods in real-world scenarios remains formidable, necessitating the exploration of more practical self-supervised image denoising. This paper focuses on self-supervised image denoising methods that offer effective solutions to address this challenge. Our comprehensive review thoroughly analyzes the latest advancements in self-supervised image denoising approaches, categorizing them into three distinct classes: General methods, Blind Spot Network (BSN)-based methods, and Transformer-based methods. For each class, we provide a concise theoretical analysis along with their practical applications. To assess the effectiveness of these methods, we present both quantitative and qualitative experimental results on various datasets, utilizing classical algorithms as benchmarks. Additionally, we critically discuss the current limitations of these methods and propose promising directions for future research. By offering a detailed overview of recent developments in self-supervised image denoising, this review serves as an invaluable resource for researchers and practitioners in the field, facilitating a deeper understanding of this emerging domain and inspiring further advancements.
Paper Structure (20 sections, 42 equations, 11 figures, 14 tables, 1 algorithm)

This paper contains 20 sections, 42 equations, 11 figures, 14 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Self-supervised image denoising methods
  3. General self-supervised image denoising methods
  4. Unpaired noisy-clean images methods
  5. Methods relying on artificially generated noisy-noisy pairs
  6. Methods relying on only single noisy images
  7. BSN-based self-supervised image denoising methods
  8. Mask in input methods
  9. Mask in network methods
  10. Transformer-based self-supervised image denoising methods
  11. Datasets and Evaluation Metrics
  12. Datasets
  13. Evaluation Metrics
  14. Experiments
  15. Synthetic noise denoising on grayscale images
  16. ...and 5 more sections

Figures (11)

  • Figure 1: Outline of the survey.
  • Figure 2: Different mask in input strategies
  • Figure 3: Different mask in network strategies
  • Figure 4: Comparison of different models on denoising BSD68 roth2005fields dataset with Gaussian noise of $\sigma$=25 and $\sigma$=50, respectively.
  • Figure 5: Visual Comparison of different methods denoising for grayscale images in BSD68 roth2005fields and Set12 dabov2007image with Gaussion noise $\sigma=25$.
  • ...and 6 more figures