Image denoising (removal of additive white Gaussian noise from an image) is one of the oldest and most studied problems in image processing. An extensive work over several decades has led to thousands of papers on this subject, and to many well-performing algorithms for this task. Indeed, 10 years ago, these achievements have led some researchers to suspect that "Denoising is Dead", in the sense that all that can be achieved in this domain has already been obtained. However, this turned out to be far from the truth, with the penetration of deep learning (DL) into image processing. The era of DL brought a revolution to image denoising, both by taking the lead in today's ability for noise removal in images, and by broadening the scope of denoising problems being treated. Our paper starts by describing this evolution, highlighting in particular the tension and synergy that exist between classical approaches and modern DL-based alternatives in design of image denoisers.
The recent transitions in the field of image denoising go far beyond the ability to design better denoisers. In the 2nd part of this paper we focus on recently discovered abilities and prospects of image denoisers. We expose the possibility of using denoisers to serve other problems, such as regularizing general inverse problems and serving as the prime engine in diffusion-based image synthesis. We also unveil the idea that denoising and other inverse problems might not have a unique solution as common algorithms would have us believe. Instead, we describe constructive ways to produce randomized and diverse high quality results for inverse problems, all fueled by the progress that DL brought to image denoising.
This survey paper aims to provide a broad view of the history of image denoising and closely related topics. Our aim is to give a better context to recent discoveries, and to the influence of DL in our domain.
Image denoising is a typical ill-posed problem due to complex degradation. Leading methods based on normalizing flows have tried to solve this problem with an invertible transformation instead of a deterministic mapping. However, the implicit bijective mapping is not explored well. Inspired by a latent observation that noise tends to appear in the high-frequency part of the image, we propose a fully invertible denoising method that injects the idea of disentangled learning into a general invertible neural network to split noise from the high-frequency part. More specifically, we decompose the …
Harbin Institute of Technology（哈尔滨工业大学）；The Hong Kong Polytechnic University（香港理工大学）；Graz University of Technology（格拉茨技术大学）；Xi’an Jiaotong University（西安交通大学）
Discriminative model learning for image denoising has been recently attracting considerable attentions due to its favorable denoising performance. In this paper, we take one step forward by investigating the construction of feed-forward denoising convolutional neural networks (DnCNNs) to embrace the progress in very deep architecture, learning algorithm, and regularization method into image denoising. Specifically, residual learning and batch normalization are utilized to speed up the training process as well as boost the denoising performance. Different from the existing discriminative denois…
Recent developments in deep learning have revolutionized the paradigm of image restoration. However, its applications on real image denoising are still limited, due to its sensitivity to training data and the complex nature of real image noise. In this work, we combine the robustness merit of model-based approaches and the learning power of data-driven approaches for real image denoising. Specifically, by integrating graph Laplacian regularization as a trainable module into a deep learning framework, we are less susceptible to overfitting than pure CNN-based approaches, achieving higher robust…
Hyperspectral image (HSI) denoising is a crucial preprocessing procedure for the subsequent HSI applications. Unfortunately, though witnessing the development of deep learning in HSI denoising area, existing convolution-based methods face the trade-off between computational efficiency and capability to model non-local characteristics of HSI. In this paper, we propose a Spatial-Spectral Transformer (SST) to alleviate this problem. To fully explore intrinsic similarity characteristics in both spatial dimension and spectral dimension, we conduct non-local spatial self-attention and global spectra…
Beyond Fixed Inference: Quantitative Flow Matching for Adaptive Image Denoising
School of Mathematical Sciences, Capital Normal University（首都师范大学数学科学学院）；National Center for Applied Mathematics Beijing, Capital Normal University（首都师范大学北京国家应用数学中心）；Academy for Multidisciplinary Studies, Capital Normal University（首都师范大学交叉科学研究院）；Institute of Nuclear and New Energy Technology, Tsinghua University（清华大学核能与新能源技术研究院）
Beyond Model Design: Data-Centric Training and Self-Ensemble for Gaussian Color Image Denoising
Hefei University of Technology（合肥工业大学）；Hangzhou Dianzi University（杭州电子科技大学）；Jinan University（暨南大学）；South China Agricultural University（华南农业大学）；The University of Tokyo（东京大学）
École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
Image denoising is a classic restoration problem. Yet, current deep learning methods are subject to the problems of generalization and interpretability. To mitigate these problems, in this project, we present a framework that is capable of controllable, confidence-based noise removal. The framework is based on the fusion between two different denoised images, both derived from the same noisy input. One of the two is denoised using generic algorithms (e.g. Gaussian), which make few assumptions on the input images, therefore, generalize in all scenarios. The other is denoised using deep learning…
Pan-denoising: Guided Hyperspectral Image Denoising via Weighted Represent Coefficient Total Variation
School of Mathematics and Statistics, Northwestern Polytechnical University（西北工业大学数学与统计学院）；Research and Development Institute of Northwestern Polytechnical University in Shenzhen（西北工业大学深圳研究院）
Inception Institute of Artificial Intelligence（人工智能 inception 研究院）；University of California, Merced（加州大学默塞德分校）；Google Research（谷歌研究院）
The availability of large-scale datasets has helped unleash the true potential of deep convolutional neural networks (CNNs). However, for the single-image denoising problem, capturing a real dataset is an unacceptably expensive and cumbersome procedure. Consequently, image denoising algorithms are mostly developed and evaluated on synthetic data that is usually generated with a widespread assumption of additive white Gaussian noise (AWGN). While the CNNs achieve impressive results on these synthetic datasets, they do not perform well when applied on real camera images, as reported in recent be…
It was recently demonstrated in [Chaudhury et al.,Non-Local Euclidean Medians,2012] that the denoising performance of Non-Local Means (NLM) can be improved at large noise levels by replacing the mean by the robust Euclidean median. Numerical experiments on synthetic and natural images showed that the latter consistently performed better than NLM beyond a certain noise level, and significantly so for images with sharp edges. The Euclidean mean and median can be put into a common regression (on the patch space) framework, in which the l_2 norm of the residuals is considered in the former, while …
Over the last decades, images have become an important source of information in many domains, thus their high quality has become necessary to acquire better information. One of the important issues that arise is image denoising, which means recovering a signal from inaccurately and/or partially measured samples. This interpretation is highly correlated to the compressive sensing theory, which is a revolutionary technology and implies that if a signal is sparse then the original signal can be obtained from a few measured values, which are much less, than the ones suggested by other used theorie…
Duke University（杜克大学）；Télécom ParisTech, Université Paris-Saclay（巴黎高科电信学院，巴黎-萨克雷大学）；Université Paris Descartes（巴黎笛卡尔大学）；Universidad de la República（共和国大学）
Recently, impressive denoising results have been achieved by Bayesian approaches which assume Gaussian models for the image patches. This improvement in performance can be attributed to the use of per-patch models. Unfortunately such an approach is particularly unstable for most inverse problems beyond denoising. In this work, we propose the use of a hyperprior to model image patches, in order to stabilize the estimation procedure. There are two main advantages to the proposed restoration scheme: Firstly it is adapted to diagonal degradation matrices, and in particular to missing data problems…
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）；Chung-Ang University Hospital（中央大学医院）；Chung-Ang University College of Medicine（中央大学医学院）
Patient scans from MRI often suffer from noise, which hampers the diagnostic capability of such images. As a method to mitigate such artifact, denoising is largely studied both within the medical imaging community and beyond the community as a general subject. However, recent deep neural network-based approaches mostly rely on the minimum mean squared error (MMSE) estimates, which tend to produce a blurred output. Moreover, such models suffer when deployed in real-world sitautions: out-of-distribution data, and complex noise distributions that deviate from the usual parametric noise models. In…
The exploitation of long-term information has been a long-standing problem in video restoration. The recent BasicVSR and BasicVSR++ have shown remarkable performance in video super-resolution through long-term propagation and effective alignment. Their success has led to a question of whether they can be transferred to different video restoration tasks. In this work, we extend BasicVSR++ to a generic framework for video restoration tasks. In tasks where inputs and outputs possess identical spatial size, the input resolution is reduced by strided convolutions to maintain efficiency. With only m…
UniPET: a universal network for high-quality PET image denoising across varied dose reduction factors
School of Biological Science and Medical Engineering（生物科学与医学工程学院）；State Key Laboratory of Software Development Environment（软件开发环境国家重点实验室）；Key Laboratory of Biomechanics, Mechanobiology of Ministry of Education（教育部生物力学与机械生物学重点实验室）；Beijing Advanced Innovation Centre for Biomedical Engineering, Beihang University（北京生物医学工程先进创新中心，北航）；Department of Biomedical Engineering（生物医学工程系）；Department of Gynecology Oncology（妇科肿瘤科）；National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital（国家癌症中心/国家癌症临床研究中心/癌症医院）；Chinese Academy of Medical Sciences（中国医学科学院）；Peking Union Medical College（北京协和医学院）；Xiaomi Corporation（小米公司）
Xian Jiaotong University（西安交通大学）；The Chinese University of Hong Kong（香港中文大学）
The 3-D total variation (3DTV) is a powerful regularization term, which encodes the local smoothness prior structure underlying a hyper-spectral image (HSI), for general HSI processing tasks. This term is calculated by assuming identical and independent sparsity structures on all bands of gradient maps calculated along spatial and spectral HSI modes. This, however, is always largely deviated from the real cases, where the gradient maps are generally with different while correlated sparsity structures across all their bands. Such deviation tends to hamper the performance of the related method b…
Poisson2Gaussian: Noise Gaussianization to Enhance Image Denoising
College of AI, Tsinghua University（清华大学人工智能学院）；Department of Automation, Tsinghua University（清华大学自动化系）；School of Electronic and Information Engineering, Beihang University（北京航空航天大学电子信息工程学院）
Natural image statistics exhibit hierarchical dependencies across multiple scales. Representing such prior knowledge in non-factorial latent tree models can boost performance of image denoising, inpainting, deconvolution or reconstruction substantially, beyond standard factorial "sparse" methodology. We derive a large scale approximate Bayesian inference algorithm for linear models with non-factorial (latent tree-structured) scale mixture priors. Experimental results on a range of denoising and inpainting problems demonstrate substantially improved performance compared to MAP estimation or to …
Carl Zeiss AG（卡尔蔡司公司）；Friedrich Miescher Institute for Biomedical Research（弗里德里希·米歇尔生物医学研究所）；Fondazione Human Technopole（人类技术中心基金会）
In recent years, neural network based image denoising approaches have revolutionized the analysis of biomedical microscopy data. Self-supervised methods, such as Noise2Void (N2V), are applicable to virtually all noisy datasets, even without dedicated training data being available. Arguably, this facilitated the fast and widespread adoption of N2V throughout the life sciences. Unfortunately, the blind-spot training underlying N2V can lead to rather visible checkerboard artifacts, thereby reducing the quality of final predictions considerably. In this work, we present two modifications to the va…
GAN-Based Architecture for Low-dose Computed Tomography Imaging Denoising
College of Life Science and Technology, Huazhong University of Science and Technology（华中科技大学生命科学技术学院）；New York University Shanghai（上海纽约大学）；School of Life Sciences and Biotechnology, Shanghai Jiao Tong University（上海交通大学生命科学技术学院）
A flexible and accurate total variation and cascaded denoisers-based image reconstruction algorithm for hyperspectrally compressed ultrafast photography
