We propose an adaptive learning procedure to learn patch-based image priors for image denoising. The new algorithm, called the Expectation-Maximization (EM) adaptation, takes a generic prior learned from a generic external database and adapts it to the noisy image to generate a specific prior. Different from existing methods that combine internal and external statistics in ad-hoc ways, the proposed algorithm is rigorously derived from a Bayesian hyper-prior perspective. There are two contributions of this paper: First, we provide full derivation of the EM adaptation algorithm and demonstrate methods to improve the computational complexity. Second, in the absence of the latent clean image, we show how EM adaptation can be modified based on pre-filtering. Experimental results show that the proposed adaptation algorithm yields consistently better denoising results than the one without adaptation and is superior to several state-of-the-art algorithms.
Korea Advanced Institute of Science and Technology（韩国科学技术院）
In recent years, a ton of research has been conducted on real image denoising tasks. However, the efforts are more focused on improving real image denoising through creating a better network architecture. We explore a different direction where we propose to improve real image denoising performance through a better learning strategy that can enable test-time adaptation on the multi-task network. The learning strategy is two stages where the first stage pre-train the network using meta-auxiliary learning to get better meta-initialization. Meanwhile, we use meta-learning for fine-tuning (meta-tra…
Inner Mongolia University（内蒙古大学）；University of Hong Kong（香港大学）
Non-local self-similarity based low rank algorithms are the state-of-the-art methods for image denoising. In this paper, a new method is proposed by solving two issues: how to improve similar patches matching accuracy and build an appropriate low rank matrix approximation model for Gaussian noise. For the first issue, similar patches can be found locally or globally. Local patch matching is to find similar patches in a large neighborhood which can alleviate noise effect, but the number of patches may be insufficient. Global patch matching is to determine enough similar patches but the error ra…
Technion Institute of Technology（以色列理工学院）；Google Research（谷歌研究院）
Image denoising is a well studied problem with an extensive activity that has spread over several decades. Despite the many available denoising algorithms, the quest for simple, powerful and fast denoisers is still an active and vibrant topic of research. Leading classical denoising methods are typically designed to exploit the inner structure in images by modeling local overlapping patches, while operating in an unsupervised fashion. In contrast, recent newcomers to this arena are supervised and universal neural-network-based methods that bypass this modeling altogether, targeting the inferen…
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 …
Institut de Mathématiques de Bordeaux, CNRS, Université de Bordeaux, Bordeaux INP（波尔多数学研究所、法国国家科学研究中心、波尔多大学、波尔多国立理工学院）；University of California, San Diego（加利福尼亚大学圣地亚哥分校）
Patch priors have become an important component of image restoration. A powerful approach in this category of restoration algorithms is the popular Expected Patch Log-Likelihood (EPLL) algorithm. EPLL uses a Gaussian mixture model (GMM) prior learned on clean image patches as a way to regularize degraded patches. In this paper, we show that a generalized Gaussian mixture model (GGMM) captures the underlying distribution of patches better than a GMM. Even though GGMM is a powerful prior to combine with EPLL, the non-Gaussianity of its components presents major challenges to be applied to a comp…
Many patch-based image denoising algorithms can be formulated as applying a smoothing filter to the noisy image. Expressed as matrices, the smoothing filters must be row normalized so that each row sums to unity. Surprisingly, if we apply a column normalization before the row normalization, the performance of the smoothing filter can often be significantly improved. Prior works showed that such performance gain is related to the Sinkhorn-Knopp balancing algorithm, an iterative procedure that symmetrizes a row-stochastic matrix to a doubly-stochastic matrix. However, a complete understanding of…
Fully supervised deep-learning based denoisers are currently the most performing image denoising solutions. However, they require clean reference images. When the target noise is complex, e.g. composed of an unknown mixture of primary noises with unknown intensity, fully supervised solutions are limited by the difficulty to build a suited training set for the problem. This paper proposes a gradual denoising strategy that iteratively detects the dominating noise in an image, and removes it using a tailored denoiser. The method is shown to keep up with state of the art blind denoisers on mixture…
Recent advances in adaptive Markov chain Monte Carlo (AMCMC) include the need for regional adaptation in situations when the optimal transition kernel is different across different regions of the sample space. Motivated by these findings, we propose a mixture-based approach to determine the partition needed for regional AMCMC. The mixture model is fitted using an online EM algorithm (see Andrieu and Moulines, 2006) which allows us to bypass simultaneously the heavy computational load and to implement the regional adaptive algorithm with online recursion (RAPTOR). The method is tried on simulat…
KAUST（阿卜杜拉国王科技大学）；The University of Sydney（悉尼大学）；Shanghai AI Laboratory（上海人工智能实验室）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；SenseTime Research（商汤科技研究院）；Qing Yuan Research Institute, Shanghai Jiao Tong University（上海交通大学清源研究院）
Imaging is usually a mixture problem of incomplete color sampling, noise degradation, and limited resolution. This mixture problem is typically solved by a sequential solution that applies demosaicing (DM), denoising (DN), and super-resolution (SR) sequentially in a fixed and predefined pipeline (execution order of tasks), DM$\to$DN$\to$SR. The most recent work on image processing focuses on developing more sophisticated architectures to achieve higher image quality. Little attention has been paid to the design of the pipeline, and it is still not clear how significant the pipeline is to image…
Indian Institute of Technology, Hyderabad（印度理工学院海得拉巴分校）；Indian Institute of Science（印度科学学院）
The bilateral filter has diverse applications in image processing, computer vision, and computational photography. In particular, this non-linear filter is quite effective in denoising images corrupted with additive Gaussian noise. The filter, however, is known to perform poorly at large noise levels. Several adaptations of the filter have been proposed in the literature to address this shortcoming, but often at an added computational cost. In this paper, we report a simple yet effective modification that improves the denoising performance of the bilateral filter at almost no additional cost. …
Nonlocal image representation has been successfully used in many image-related inverse problems including denoising, deblurring and deblocking. However, a majority of reconstruction methods only exploit the nonlocal self-similarity (NSS) prior of the degraded observation image, it is very challenging to reconstruct the latent clean image. In this paper we propose a novel model for image denoising via group sparsity residual and external NSS prior. To boost the performance of image denoising, the concept of group sparsity residual is proposed, and thus the problem of image denoising is transfor…
This paper proposes a non-data-driven deep neural network for spectral image recovery problems such as denoising, single hyperspectral image super-resolution, and compressive spectral imaging reconstruction. Unlike previous methods, the proposed approach, dubbed Mixture-Net, implicitly learns the prior information through the network. Mixture-Net consists of a deep generative model whose layers are inspired by the linear and non-linear low-rank mixture models, where the recovered image is composed of a weighted sum between the linear and non-linear decomposition. Mixture-Net also provides a lo…
Image denoising and demosaicking are the most important early stages in digital camera pipelines. They constitute a severely ill-posed problem that aims at reconstructing a full color image from a noisy color filter array (CFA) image. In most of the literature, denoising and demosaicking are treated as two independent problems, without considering their interaction, or asking which should be applied first. Several recent works have started addressing them jointly in works that involve heavy weight CNNs, thus incompatible with low power portable imaging devices. Hence, the question of how to co…
Xiamen University（厦门大学）；South China University of Technology（华南理工大学）；Columbia University（哥伦比亚大学）
We devise a new regularization, called self-verification, for image denoising. This regularization is formulated using a deep image prior learned by the network, rather than a traditional predefined prior. Specifically, we treat the output of the network as a ``prior'' that we denoise again after ``re-noising''. The comparison between the again denoised image and its prior can be interpreted as a self-verification of the network's denoising ability. We demonstrate that self-verification encourages the network to capture low-level image statistics needed to restore the image. Based on this self…
This paper proposes a general framework for internal patch-based image restoration based on Conditional Random Fields (CRF). Unlike related models based on Markov Random Fields (MRF), our approach explicitly formulates the posterior distribution for the entire image. The potential functions are taken as proportional to the product of a likelihood and prior for each patch. By assuming identical parameters for similar patches, our approach can be classified as a model-based non-local method. For the prior term in the potential function of the CRF model, multivariate Gaussians and multivariate sc…
Sublinear Variational Optimization of Gaussian Mixture Models with Millions to Billions of Parameters
Faculty VI Carl von Ossietzky University Oldenburg（卡尔·奥西埃茨基大学第六学院）；Artificial Intelligence Lab, Department of Computer Science, Faculty of Mathematics, Computer Science and Physics University of Innsbruck（人工智能实验室，计算机科学系，数学、计算机科学与物理学学院因斯布鲁克大学）；Data Analytics and AI, Faculty 3 Frankfurt University of Applied Sciences（数据分析与人工智能，第三学院法兰克福应用科学大学）
University of Washington（华盛顿大学）；Purdue University（普渡大学）；GE Healthcare Technologies（通用电气医疗技术公司）；University of Notre Dame（圣母大学）
Markov random fields (MRFs) have been widely used as prior models in various inverse problems such as tomographic reconstruction. While MRFs provide a simple and often effective way to model the spatial dependencies in images, they suffer from the fact that parameter estimation is difficult. In practice, this means that MRFs typically have very simple structure that cannot completely capture the subtle characteristics of complex images. In this paper, we present a novel Gaussian mixture Markov random field model (GM-MRF) that can be used as a very expressive prior model for inverse problems su…
The Chinese University of Hong Kong（香港中文大学）；Tianjin University（天津大学）
Most existing image denoising approaches assumed the noise to be homogeneous white Gaussian distributed with known intensity. However, in real noisy images, the noise models are usually unknown beforehand and can be much more complex. This paper addresses this problem and proposes a novel blind image denoising algorithm to recover the clean image from noisy one with the unknown noise model. To model the empirical noise of an image, our method introduces the mixture of Gaussian distribution, which is flexible enough to approximate different continuous distributions. The problem of blind image d…
With the advent of advances in self-supervised learning, paired clean-noisy data are no longer required in deep learning-based image denoising. However, existing blind denoising methods still require the assumption with regard to noise characteristics, such as zero-mean noise distribution and pixel-wise noise-signal independence; this hinders wide adaptation of the method in the medical domain. On the other hand, unpaired learning can overcome limitations related to the assumption on noise characteristics, which makes it more feasible for collecting the training data in real-world scenarios. I…
Hanyang University（汉阳大学）；Chungnam National University（忠南国立大学）；SK T-Brain
Under certain statistical assumptions of noise, recent self-supervised approaches for denoising have been introduced to learn network parameters without true clean images, and these methods can restore an image by exploiting information available from the given input (i.e., internal statistics) at test time. However, self-supervised methods are not yet combined with conventional supervised denoising methods which train the denoising networks with a large number of external training samples. Thus, we propose a new denoising approach that can greatly outperform the state-of-the-art supervised de…
University of Shanghai for Science and Technology（上海理工大学）；Universität Hamburg（汉堡大学）；ComOriginMat Inc.（科里金马特公司）；Chongqing University（重庆大学）；University of Electronic Science and Technology of China（电子科技大学）；University of Surrey（萨里大学）
Prototype-Based Pseudo-Label Denoising for Source-Free Domain Adaptation in Remote Sensing Semantic Segmentation
College of Computer Science, Sichuan University（四川大学计算机科学学院）；College of Computer Science and Cyber Security, Chengdu University of Technology（成都理工大学计算机科学与网络安全学院）
Baidu Inc.（百度公司）；Wuhan University of Science and Technology（武汉科技大学）
Recent progress in diffusion models has revolutionized the popular technology of text-to-image generation. While existing approaches could produce photorealistic high-resolution images with text conditions, there are still several open problems to be solved, which limits the further improvement of image fidelity and text relevancy. In this paper, we propose ERNIE-ViLG 2.0, a large-scale Chinese text-to-image diffusion model, to progressively upgrade the quality of generated images by: (1) incorporating fine-grained textual and visual knowledge of key elements in the scene, and (2) utilizing di…
DP-TTA: Test-time Adaptation for Transient Electromagnetic Signal Denoising via Dictionary-driven Prior Regularization
College of Mechanical and Electrical Engineering, Chengdu University of Technology（成都理工大学机械与电子工程学院）；City University of Hong Kong, Department of Electrical Engineering（香港城市大学电子工程系）；Sichuan Provincial Natural Resources Survey and Design Group Co., Ltd.（四川省自然资源调查设计集团有限公司）；Massey University, School of Mathematical and Computational Sciences（马斯利大学数学与计算科学学院）
A Chebyshev Confidence Guided Source-Free Domain Adaptation Framework for Medical Image Segmentation
Harbin Institute of Technology at Shenzhen（哈尔滨工业大学（深圳））；The Peng Cheng Laboratory（鹏城实验室）；Guangdong Provincial Key Laboratory of Aerospace Communication and Networking Technology（广东省航空航天通信与网络技术重点实验室）
Data61/CSIRO（澳大利亚联邦科学与工业研究组织数据61研究所）；Australian National University（澳大利亚国立大学）
In this paper, we propose an approach to the domain adaptation, dubbed Second- or Higher-order Transfer of Knowledge (So-HoT), based on the mixture of alignments of second- or higher-order scatter statistics between the source and target domains. The human ability to learn from few labeled samples is a recurring motivation in the literature for domain adaptation. Towards this end, we investigate the supervised target scenario for which few labeled target training samples per category exist. Specifically, we utilize two CNN streams: the source and target networks fused at the classifier level. …
Tel-Aviv University（特拉维夫大学）；Facebook AI Research（脸书人工智能研究院）；École Normale Supérieure Paris-Saclay（巴黎-萨克雷高等师范学院）
Generative diffusion processes are an emerging and effective tool for image and speech generation. In the existing methods, the underline noise distribution of the diffusion process is Gaussian noise. However, fitting distributions with more degrees of freedom, could help the performance of such generative models. In this work, we investigate other types of noise distribution for the diffusion process. Specifically, we show that noise from Gamma distribution provides improved results for image and speech generation. Moreover, we show that using a mixture of Gaussian noise variables in the diff…
Laboratory of Mathematics and Complex Systems (Ministry of Education of China), School of Mathematical Sciences, Beijing Normal University（北京师范大学数学科学学院，数学与复杂系统实验室（中国教育部））
We consider the inpainting problem for noisy images. It is very challenge to suppress noise when image inpainting is processed. An image patches based nonlocal variational method is proposed to simultaneously inpainting and denoising in this paper. Our approach is developed on an assumption that the small image patches should be obeyed a distribution which can be described by a high dimension Gaussian Mixture Model. By a maximum a posteriori (MAP) estimation, we formulate a new regularization term according to the log-likelihood function of the mixture model. To optimize this regularization te…
Herein, we present a system for hyperspectral image segmentation that utilizes multiple class--based denoising autoencoders which are efficiently trained. Moreover, we present a novel hyperspectral data augmentation method for labelled HSI data using linear mixtures of pixels from each class, which helps the system with edge pixels which are almost always mixed pixels. Finally, we utilize a deep neural network and morphological hole-filling to provide robust image classification. Results run on the Salinas dataset verify the high performance of the proposed algorithm.
MoASE++: Mixture of Activation Sparsity Experts with Domain-Adaptive On-policy Distillation for Continual Test Time Adaptation
Nanjing University and The Hong Kong Polytechnic University（南京大学和香港理工大学）；State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（北京大学多媒体信息处理国家重点实验室，计算机科学学院）；University of Arizona（亚利桑那大学）；Hong Kong University of Science and Technology（香港科技大学）；School of Artificial Intelligence and Robotics, Hunan University（湖南大学人工智能与机器人学院）；Nanjing University（南京大学）
Seoul National University（首尔大学）；Samsung SDS（三星SDS）
Denoising diffusion probabilistic models (DDPM) have shown remarkable performance in unconditional image generation. However, due to the stochasticity of the generative process in DDPM, it is challenging to generate images with the desired semantics. In this work, we propose Iterative Latent Variable Refinement (ILVR), a method to guide the generative process in DDPM to generate high-quality images based on a given reference image. Here, the refinement of the generative process in DDPM enables a single DDPM to sample images from various sets directed by the reference image. The proposed ILVR m…
