[论文解读] Unleashing the Power of Self-Supervised Image Denoising: A Comprehensive Review

Dan Zhang, Fangfang Zhou+5 more|arXiv (Cornell University)|Aug 1, 2023

Image and Signal Denoising Methods被引用 8

一句话总结

对自监督图像去噪方法的综合综述，分为通用、基于盲点网络（BSN）和基于Transformer的方法，提供理论见解和实验分析。

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.

研究动机与目标

• 在真实世界中没有干净真值数据的去噪挑战上进行动机阐述和绘制图谱。
• 将自监督去噪方法分为三类并总结其原理与应用。
• 在数据集上提供理论分析和实践评估，供研究者和从业者参考。

提出的方法

• 将自监督去噪方法分为通用、BSN 基于、Transformer 基于三大类。
• 概述具有代表性的方法及其核心原理，包括掩码策略和基于分数的方法。
• 讨论数据集、评估指标，以及定性和定量结果以比较方法。

实验结果

研究问题

• RQ1 哪些是主要的自监督去噪范式及其潜在假设？
• RQ2 通用、BSN 基于和 Transformer 基于方法在理论基础和实际性能上有何对比？
• RQ3 哪些数据集和指标最能揭示自监督去噪方法的优点与局限性？
• RQ4 自监督图像去噪的关键局限与未来研究的有前景方向是什么？

主要发现

• 论文提出了自监督去噪方法的三段式分类：通用、BSN 基于和 Transformer 基于。
• 提供简明的理论分析并描述各类的实际应用。
• 给出实验结果以评估在各种数据集和去噪任务上的有效性。
• 综述强调当前的局限性并提出自监督去噪未来研究的方向。