Denoising Prior Driven Deep Neural Network for Image Restoration

DeepSN-Net: Deep Semi-Smooth Newton Driven Network for Blind Image Restoration

The deep unfolding network represents a promising research avenue in image restoration. However, most current deep unfolding methodologies are anchored in first-order optimization algorithms, which suffer from sluggish convergence speed and unsatisfactory learning efficiency. In this paper, to address this issue, we first formulate an improved second-order semi-smooth Newton (ISN) algorithm, transforming the original nonlinear equations into an optimization problem amenable to network implementation. After that, we propose an innovative network architecture based on the ISN algorithm for blind image restoration, namely DeepSN-Net. To the best of our knowledge, DeepSN-Net is the first successful endeavor to design a second-order deep unfolding network for image restoration, which fills the blank of this area. Furthermore, it offers several distinct advantages: 1) DeepSN-Net provides a unified framework to a variety of image restoration tasks in both synthetic and real-world contexts, without imposing constraints on the degradation conditions. 2) The network architecture is meticulously aligned with the ISN algorithm, ensuring that each module possesses robust physical interpretability. 3) The network exhibits high learning efficiency, superior restoration accuracy and good generalization ability across 11 datasets on three typical restoration tasks. The success of DeepSN-Net on image restoration may ignite many subsequent works centered around the second-order optimization algorithms, which is good for the community.

A Femtosecond Fiber Laser-Based Compact Label-Free Multimodality Nonlinear Optical Microscopy and Its Ex Vivo Bioimaging

Nonlinear multimode imaging is a versatile tool to realize complex structural and compositional information of biological samples. In this study, we presented a novel integrated multimode nonlinear optical microscopy system by using an Er3 + -doped femtosecond fiber laser. The system could perform second harmonic generation (SHG), third harmonic generation (THG), and three-photon fluorescence (3PEF) imaging modes simultaneously. Using this imaging system, we detected signals from plant cell walls, as well as starch particles in potatoes, chloroplasts in leaves, and onion cells wall-to-membrane linkers: Hechtian strands. Visualizations of skin structures such as stratum corneum, epidermal intercellular structures, hair follicles, and collagen were also achieved by a spatial resolution of 1.67 μm for 3PEF, 1.5 μm for THG, and 2.67 μm for SHG modalities, respectively. After spatial resolution improved by changing a high N.A objective, the system could be used for a variety of biological applications, including in vivo label-free imaging of living animals and deep microscopic imaging.

DEs-Inspired Accelerated Unfolded Linearized ADMM Networks for Inverse Problems

Many research works have shown that the traditional alternating direction multiplier methods (ADMMs) can be better understood by continuous-time differential equations (DEs). On the other hand, many unfolded algorithms directly inherit the traditional iterations to build deep networks. Although they achieve superior practical performance and a faster convergence rate than traditional counterparts, there is a lack of clear insight into unfolded network structures. Thus, we attempt to explore the unfolded linearized ADMM (LADMM) from the perspective of DEs, and design more efficient unfolded networks. First, by proposing an unfolded Euler LADMM scheme and inspired by the trapezoid discretization, we design a new more accurate Trapezoid LADMM scheme. For the convenience of implementation, we provide its explicit version via a prediction-correction strategy. Then, to expand the representation space of unfolded networks, we design an accelerated variant of our Euler LADMM scheme, which can be interpreted as second-order DEs with stronger representation capabilities. To fully explore this representation space, we designed an accelerated Trapezoid LADMM scheme. To the best of our knowledge, this is the first work to explore a comprehensive connection with theoretical guarantees between unfolded ADMMs and first- (second-) order DEs. Finally, we instantiate our schemes as (A-)ELADMM and (A-)TLADMM with the proximal operators, and (A-)ELADMM-Net and (A-)TLADMM-Net with convolutional neural networks (CNNs). Extensive inverse problem experiments show that our Trapezoid LADMM schemes perform better than well-known methods.

Joint Spatial and Frequency Domain Learning for Lightweight Spectral Image Demosaicing

Conventional spectral image demosaicing algorithms rely on pixels' spatial or spectral correlations for reconstruction. Due to the missing data in the multispectral filter array (MSFA), the estimation of spatial or spectral correlations is inaccurate, leading to poor reconstruction results, and these algorithms are time-consuming. Deep learning-based spectral image demosaicing methods directly learn the nonlinear mapping relationship between 2D spectral mosaic images and 3D multispectral images. However, these learning-based methods focused only on learning the mapping relationship in the spatial domain, but neglected valuable image information in the frequency domain, resulting in limited reconstruction quality. To address the above issues, this paper proposes a novel lightweight spectral image demosaicing method based on joint spatial and frequency domain information learning. First, a novel parameter-free spectral image initialization strategy based on the Fourier transform is proposed, which leads to better initialized spectral images and eases the difficulty of subsequent spectral image reconstruction. Furthermore, an efficient spatial-frequency transformer network is proposed, which jointly learns the spatial correlations and the frequency domain characteristics. Compared to existing learning-based spectral image demosaicing methods, the proposed method significantly reduces the number of model parameters and computational complexity. Extensive experiments on simulated and real-world data show that the proposed method notably outperforms existing spectral image demosaicing methods.

Fast and Reliable Score-Based Generative Model for Parallel MRI

The score-based generative model (SGM) can generate high-quality samples, which have been successfully adopted for magnetic resonance imaging (MRI) reconstruction. However, the recent SGMs may take thousands of steps to generate a high-quality image. Besides, SGMs neglect to exploit the redundancy in space. To overcome the above two drawbacks, in this article, we propose a fast and reliable SGM (FRSGM). First, we propose deep ensemble denoisers (DEDs) consisting of SGM and the deep denoiser, which are used to solve the proximal problem of the implicit regularization term. Second, we propose a spatially adaptive self-consistency (SASC) term as the regularization term of the -space data. We use the alternating direction method of multipliers (ADMM) algorithm to solve the minimization model of compressed sensing (CS)-MRI incorporating the image prior term and the SASC term, which is significantly faster than the related works based on SGM. Meanwhile, we can prove that the iterating sequence of the proposed algorithm has a unique fixed point. In addition, the DED and the SASC term can significantly improve the generalization ability of the algorithm. The features mentioned above make our algorithm reliable, including the fixed-point convergence guarantee, the exploitation of the space, and the powerful generalization ability.

An alternating multiple residual Wasserstein regularization model for Gaussian image denoising

Residual histograms can provide meaningful statistical information in low-level visual research. However, the existing image denoising methods do not deeply explore the potential of alternate multiple residual histograms for overall optimization constraints. Considering this deficiency, this paper presents a novel unified framework of the alternating multiple residual Wasserstein regularization model (AMRW), which can tactfully embrace multiple residual Wasserstein constraints and different image prior information for image denoising. Specifically, AMRW focuses on solving the practical and meaningful problem of restoring a clean image from multiple frame degraded images. Utilizing the Wasserstein distance in the optimal transport theory, the residual histograms of the multiple degraded images are as close as possible to the referenced Gaussian noise histogram to enhance the noise estimation accuracy. Further, the proposed concrete AMRW combines the triple residual Wasserstein distance with the image total variation prior information for Gaussian image denoising. More importantly, through the alternating implementation of residual Wasserstein regularization from different image frames, the beneficial information of the image is essentially transmitted in each cycle, continuously improving the quality of the output image. Synchronously, the alternate iterative algorithm of histogram matching and Chambolle dual projection has high implementation efficiency. AMRW provides a new research idea for other visual processing tasks such as image inpainting and image deblurring. Finally, extensive numerical experiments substantiate that our AMRW can greatly boost the subjective and objective performance of the restored images compared with some popular image denoising algorithms in recent years.

Decoding Glioblastoma Heterogeneity: Neuroimaging Meets Machine Learning

Recent advancements in neuroimaging and machine learning have significantly improved our ability to diagnose and categorize isocitrate dehydrogenase (IDH)-wildtype glioblastoma, a disease characterized by notable tumoral heterogeneity, which is crucial for effective treatment. Neuroimaging techniques, such as diffusion tensor imaging and magnetic resonance radiomics, provide noninvasive insights into tumor infiltration patterns and metabolic profiles, aiding in accurate diagnosis and prognostication. Machine learning algorithms further enhance glioblastoma characterization by identifying distinct imaging patterns and features, facilitating precise diagnoses and treatment planning. Integration of these technologies allows for the development of image-based biomarkers, potentially reducing the need for invasive biopsy procedures and enabling personalized therapy targeting specific pro-tumoral signaling pathways and resistance mechanisms. Although significant progress has been made, ongoing innovation is essential to address remaining challenges and further improve these methodologies. Future directions should focus on refining machine learning models, integrating emerging imaging techniques, and elucidating the complex interplay between imaging features and underlying molecular processes. This review highlights the pivotal role of neuroimaging and machine learning in glioblastoma research, offering invaluable noninvasive tools for diagnosis, prognosis prediction, and treatment planning, ultimately improving patient outcomes. These advances in the field promise to usher in a new era in the understanding and classification of IDH-wildtype glioblastoma.

Multi-Scale Spatio-Temporal Memory Network for Lightweight Video Denoising

Deep learning-based video denoising methods have achieved great performance improvements in recent years. However, the expensive computational cost arising from sophisticated network design has severely limited their applications in real-world scenarios. To address this practical weakness, we propose a multiscale spatio-temporal memory network for fast video denoising, named MSTMN, aiming at striking an improved trade-off between cost and performance. To develop an efficient and effective algorithm for video denoising, we exploit a multiscale representation based on the Gaussian-Laplacian pyramid decomposition so that the reference frame can be restored in a coarse-to-fine manner. Guided by a model-based optimization approach, we design an effective variance estimation module, an alignment error estimation module and an adaptive fusion module for each scale of the pyramid representation. For the fusion module, we employ a reconstruction recurrence strategy to incorporate local temporal information. Moreover, we propose a memory enhancement module to exploit the global spatio-temporal information. Meanwhile, the similarity computation of the spatio-temporal memory network enables the proposed network to adaptively search the valuable information at the patch level, which avoids computationally expensive motion estimation and compensation operations. Experimental results on real-world raw video datasets have demonstrated that the proposed lightweight network outperforms current state-of-the-art fast video denoising algorithms such as FastDVDnet, EMVD, and ReMoNet with fewer computational costs.

Multi-rater Prism: Learning self-calibrated medical image segmentation from multiple raters

In medical image segmentation, it is often necessary to collect opinions from multiple experts to make the final decision. This clinical routine helps to mitigate individual bias. However, when data is annotated by multiple experts, standard deep learning models are often not applicable. In this paper, we propose a novel neural network framework called Multi-rater Prism (MrPrism) to learn medical image segmentation from multiple labels. Inspired by iterative half-quadratic optimization, MrPrism combines the task of assigning multi-rater confidences and calibrated segmentation in a recurrent manner. During this process, MrPrism learns inter-observer variability while taking into account the image's semantic properties and finally converges to a self-calibrated segmentation result reflecting inter-observer agreement. Specifically, we propose Converging Prism (ConP) and Diverging Prism (DivP) to iteratively process the two tasks. ConP learns calibrated segmentation based on multi-rater confidence maps estimated by DivP, and DivP generates multi-rater confidence maps based on segmentation masks estimated by ConP. Experimental results show that the two tasks can mutually improve each other through this recurrent process. The final converged segmentation result of MrPrism outperforms state-of-the-art (SOTA) methods for a wide range of medical image segmentation tasks. The code is available at https://github.com/WuJunde/MrPrism.

Deep denoiser prior driven relaxed iterated Tikhonov method for low-count PET image restoration

Objective. Low-count positron emission tomography (PET) imaging is an efficient way to promote more widespread use of PET because of its short scan time and low injected activity. However, this often leads to low-quality PET images with clinical image reconstruction, due to high noise and blurring effects. Existing PET image restoration (IR) methods hinder their own restoration performance due to the semi-convergence property and the lack of suitable denoiser prior.Approach. To overcome these limitations, we propose a novel deep plug-and-play IR method called Deep denoiser Prior driven Relaxed Iterated Tikhonov method (DP-RI-Tikhonov). Specifically, we train a deep convolutional neural network denoiser to generate a flexible deep denoiser prior to handle high noise. Then, we plug the deep denoiser prior as a modular part into a novel iterative optimization algorithm to handle blurring effects and propose an adaptive parameter selection strategy for the iterative optimization algorithm.Main results. Simulation results show that the deep denoiser prior plays the role of reducing noise intensity, while the novel iterative optimization algorithm and adaptive parameter selection strategy can effectively eliminate the semi-convergence property. They enable DP-RI-Tikhonov to achieve an average quantitative result (normalized root mean square error, structural similarity) of (0.1364, 0.9574) at the stopping iteration, outperforming a conventional PET IR method with an average quantitative result of (0.1533, 0.9523) and a state-of-the-art deep plug-and-play IR method with an average quantitative result of (0.1404, 0.9554). Moreover, the advantage of DP-RI-Tikhonov becomes more obvious at the last iteration. Experiments on six clinical whole-body PET images further indicate that DP-RI-Tikhonov successfully reduces noise intensity and recovers fine details, recovering sharper and more uniform images than the comparison methods.Significance. DP-RI-Tikhonov's ability to reduce noise intensity and effectively eliminate the semi-convergence property overcomes the limitations of existing methods. This advancement may have substantial implications for other medical IR.

Imaging quality enhancement in photon-counting single-pixel imaging via an ADMM-based deep unfolding network in small animal fluorescence imaging

Photon-counting single-pixel imaging (SPI) can image under low-light conditions with high-sensitivity detection. However, the imaging quality of these systems will degrade due to the undersampling and intrinsic photon-noise in practical applications. Here, we propose a deep unfolding network based on the Bayesian maximum a posterior (MAP) estimation and alternating direction method of multipliers (ADMM) algorithm. The reconstruction framework adopts a learnable denoiser by convolutional neural network (CNN) instead of explicit function with hand-crafted prior. Our method enhances the imaging quality compared to traditional methods and data-driven CNN under different photon-noise levels at a low sampling rate of 8%. Using our method, the sensitivity of photon-counting SPI prototype system for fluorescence imaging can reach 7.4 pmol/ml. In-vivo imaging of a mouse bearing tumor demonstrates an 8-times imaging efficiency improvement.

Spectral Super-Resolution via Model-Guided Cross-Fusion Network

Spectral super-resolution, which reconstructs a hyperspectral image (HSI) from a single red-green-blue (RGB) image, has acquired more and more attention. Recently, convolution neural networks (CNNs) have achieved promising performance. However, they often fail to simultaneously exploit the imaging model of the spectral super-resolution and complex spatial and spectral characteristics of the HSI. To tackle the above problems, we build a novel cross fusion (CF)-based model-guided network (called SSRNet) for spectral super-resolution. In specific, based on the imaging model, we unfold the spectral super-resolution into the HSI prior learning (HPL) module and imaging model guiding (IMG) module. Instead of just modeling one kind of image prior, the HPL module is composed of two subnetworks with different structures, which can effectively learn the complex spatial and spectral priors of the HSI, respectively. Furthermore, a CF strategy is used to establish the connection between the two subnetworks, which further improves the learning performance of the CNN. The IMG module results in solving a strong convex optimization problem, which adaptively optimizes and merges the two features learned by the HPL module by exploiting the imaging model. The two modules are alternately connected to achieve optimal HSI reconstruction performance. Experiments on both the simulated and real data demonstrate that the proposed method can achieve superior spectral reconstruction results with relatively small model size. The code will be available at https://github.com/renweidian.

Sensitivity Decouple Learning for Image Compression Artifacts Reduction

With the benefit of deep learning techniques, recent researches have made significant progress in image compression artifacts reduction. Despite their improved performances, prevailing methods only focus on learning a mapping from the compressed image to the original one but ignore the intrinsic attributes of the given compressed images, which greatly harms the performance of downstream parsing tasks. Different from these methods, we propose to decouple the intrinsic attributes into two complementary features for artifacts reduction, i.e., the compression-insensitive features to regularize the high-level semantic representations during training and the compression-sensitive features to be aware of the compression degree. To achieve this, we first employ adversarial training to regularize the compressed and original encoded features for retaining high-level semantics, and we then develop the compression quality-aware feature encoder for compression-sensitive features. Based on these dual complementary features, we propose a Dual Awareness Guidance Network (DAGN) to utilize these awareness features as transformation guidance during the decoding phase. In our proposed DAGN, we develop a cross-feature fusion module to maintain the consistency of compression-insensitive features by fusing compression-insensitive features into the artifacts reduction baseline. Our method achieves an average 2.06 dB PSNR gains on BSD500, outperforming state-of-the-art methods, and only requires 29.7 ms to process one image on BSD500. Besides, the experimental results on LIVE1 and LIU4K also demonstrate the efficiency, effectiveness, and superiority of the proposed method in terms of quantitative metrics, visual quality, and downstream machine vision tasks.

Zero-shot denoising of microscopy images recorded at high-resolution limits

Conventional and electron microscopy visualize structures in the micrometer to nanometer range, and such visualizations contribute decisively to our understanding of biological processes. Due to different factors in recording processes, microscopy images are subject to noise. Especially at their respective resolution limits, a high degree of noise can negatively effect both image interpretation by experts and further automated processing. However, the deteriorating effects of strong noise can be alleviated to a large extend by image enhancement algorithms. Because of the inherent high noise, a requirement for such algorithms is their applicability directly to noisy images or, in the extreme case, to just a single noisy image without a priori noise level information (referred to as blind zero-shot setting). This work investigates blind zero-shot algorithms for microscopy image denoising. The strategies for denoising applied by the investigated approaches include: filtering methods, recent feed-forward neural networks which were amended to be trainable on noisy images, and recent probabilistic generative models. As datasets we consider transmission electron microscopy images including images of SARS-CoV-2 viruses and fluorescence microscopy images. A natural goal of denoising algorithms is to simultaneously reduce noise while preserving the original image features, e.g., the sharpness of structures. However, in practice, a tradeoff between both aspects often has to be found. Our performance evaluations, therefore, focus not only on noise removal but set noise removal in relation to a metric which is instructive about sharpness. For all considered approaches, we numerically investigate their performance, report their denoising/sharpness tradeoff on different images, and discuss future developments. We observe that, depending on the data, the different algorithms can provide significant advantages or disadvantages in terms of their noise removal vs. sharpness preservation capabilities, which may be very relevant for different virological applications, e.g., virological analysis or image segmentation.

An Interpretable Unsupervised Unrolling Network for Hyperspectral Pansharpening

Existing deep convolutional neural networks (CNNs) have recently achieved great success in pansharpening. However, most deep CNN-based pansharpening models are based on "black-box" architecture and require supervision, making these methods rely heavily on the ground-truth data and lose their interpretability for specific problems during network training. This study proposes a novel interpretable unsupervised end-to-end pansharpening network, called as IU2PNet, which explicitly encodes the well-studied pansharpening observation model into an unsupervised unrolling iterative adversarial network. Specifically, we first design a pansharpening model, whose iterative process can be computed by the half-quadratic splitting algorithm. Then, the iterative steps are unfolded into a deep interpretable iterative generative dual adversarial network (iGDANet). Generator in iGDANet is interwoven by multiple deep feature pyramid denoising modules and deep interpretable convolutional reconstruction modules. In each iteration, the generator establishes an adversarial game with the spatial and spectral discriminators to update both spectral and spatial information without ground-truth images. Extensive experiments show that, compared with the state-of-the-art methods, our proposed IU2PNet exhibits very competitive performance in terms of quantitative evaluation metrics and qualitative visual effects.

MGDUN: An interpretable network for multi-contrast MRI image super-resolution reconstruction

Magnetic resonance imaging (MRI) Super-Resolution (SR) aims to obtain high resolution (HR) images with more detailed information for precise diagnosis and quantitative image analysis. Deep unfolding networks outperform general MRI SR reconstruction methods by providing better performance and improved interpretability, which enhance the trustworthiness required in clinical practice. Additionally, current SR reconstruction techniques often rely on a single contrast or a simple multi-contrast fusion mechanism, ignoring the complex relationships between different contrasts. To address these issues, in this paper, we propose a Model-Guided multi-contrast interpretable Deep Unfolding Network (MGDUN) for medical image SR reconstruction, which explicitly incorporates the well-studied multi-contrast MRI observation model into an unfolding iterative network. Specifically, we manually design an objective function for MGDUN that can be iteratively computed by the half-quadratic splitting algorithm. The iterative MGDUN algorithm is unfolded into a special model-guided deep unfolding network that explicitly takes into account both the multi-contrast relationship matrix and the MRI observation matrix during the end-to-end optimization process. Extensive experimental results on the multi-contrast IXI dataset and the BraTs 2019 dataset demonstrate the superiority of our proposed model, with PSNR reaching 37.3366 and 35.9690 respectively. Our proposed MGDUN provides a promising solution for multi-contrast MR image super-resolution reconstruction. Code is available at https://github.com/yggame/MGDUN.

Optimization-Inspired Learning With Architecture Augmentations and Control Mechanisms for Low-Level Vision

In recent years, there has been a growing interest in combining learnable modules with numerical optimization to solve low-level vision tasks. However, most existing approaches focus on designing specialized schemes to generate image/feature propagation. There is a lack of unified consideration to construct propagative modules, provide theoretical analysis tools, and design effective learning mechanisms. To mitigate the above issues, this paper proposes a unified optimization-inspired learning framework to aggregate Generative, Discriminative, and Corrective (GDC for short) principles with strong generalization for diverse optimization models. Specifically, by introducing a general energy minimization model and formulating its descent direction from different viewpoints (i.e., in a generative manner, based on the discriminative metric and with optimality-based correction), we construct three propagative modules to effectively solve the optimization models with flexible combinations. We design two control mechanisms that provide the non-trivial theoretical guarantees for both fully- and partially-defined optimization formulations. Under the support of theoretical guarantees, we can introduce diverse architecture augmentation strategies such as normalization and search to ensure stable propagation with convergence and seamlessly integrate the suitable modules into the propagation respectively. Extensive experiments across varied low-level vision tasks validate the efficacy and adaptability of GDC.

Image De-Raining Transformer

Existing deep learning based de-raining approaches have resorted to the convolutional architectures. However, the intrinsic limitations of convolution, including local receptive fields and independence of input content, hinder the model's ability to capture long-range and complicated rainy artifacts. To overcome these limitations, we propose an effective and efficient transformer-based architecture for the image de-raining. First, we introduce general priors of vision tasks, i.e., locality and hierarchy, into the network architecture so that our model can achieve excellent de-raining performance without costly pre-training. Second, since the geometric appearance of rainy artifacts is complicated and of significant variance in space, it is essential for de-raining models to extract both local and non-local features. Therefore, we design the complementary window-based transformer and spatial transformer to enhance locality while capturing long-range dependencies. Besides, to compensate for the positional blindness of self-attention, we establish a separate representative space for modeling positional relationship, and design a new relative position enhanced multi-head self-attention. In this way, our model enjoys powerful abilities to capture dependencies from both content and position, so as to achieve better image content recovery while removing rainy artifacts. Experiments substantiate that our approach attains more appealing results than state-of-the-art methods quantitatively and qualitatively.

Low-Rankness Guided Group Sparse Representation for Image Restoration

As a spotlighted nonlocal image representation model, group sparse representation (GSR) has demonstrated a great potential in diverse image restoration tasks. Most of the existing GSR-based image restoration approaches exploit the nonlocal self-similarity (NSS) prior by clustering similar patches into groups and imposing sparsity to each group coefficient, which can effectively preserve image texture information. However, these methods have imposed only plain sparsity over each individual patch of the group, while neglecting other beneficial image properties, e.g., low-rankness (LR), leads to degraded image restoration results. In this article, we propose a novel low-rankness guided group sparse representation (LGSR) model for highly effective image restoration applications. The proposed LGSR jointly utilizes the sparsity and LR priors of each group of similar patches under a unified framework. The two priors serve as the complementary priors in LGSR for effectively preserving the texture and structure information of natural images. Moreover, we apply an alternating minimization algorithm with an adaptively adjusted parameter scheme to solve the proposed LGSR-based image restoration problem. Extensive experiments are conducted to demonstrate that the proposed LGSR achieves superior results compared with many popular or state-of-the-art algorithms in various image restoration tasks, including denoising, inpainting, and compressive sensing (CS).

Dynamic Path-Controllable Deep Unfolding Network for Compressive Sensing

Deep unfolding network (DUN) that unfolds the optimization algorithm into a deep neural network has achieved great success in compressive sensing (CS) due to its good interpretability and high performance. Each stage in DUN corresponds to one iteration in optimization. At the test time, all the sampling images generally need to be processed by all stages, which comes at a price of computation burden and is also unnecessary for the images whose contents are easier to restore. In this paper, we focus on CS reconstruction and propose a novel Dynamic Path-Controllable Deep Unfolding Network (DPC-DUN). DPC-DUN with our designed path-controllable selector can dynamically select a rapid and appropriate route for each image and is slimmable by regulating different performance-complexity tradeoffs. Extensive experiments show that our DPC-DUN is highly flexible and can provide excellent performance and dynamic adjustment to get a suitable tradeoff, thus addressing the main requirements to become appealing in practice. Codes are available at https://github.com/songjiechong/DPC-DUN.

Bayesian Image Super-Resolution With Deep Modeling of Image Statistics

Modeling statistics of image priors is useful for image super-resolution, but little attention has been paid from the massive works of deep learning-based methods. In this work, we propose a Bayesian image restoration framework, where natural image statistics are modeled with the combination of smoothness and sparsity priors. Concretely, first we consider an ideal image as the sum of a smoothness component and a sparsity residual, and model real image degradation including blurring, downscaling, and noise corruption. Then, we develop a variational Bayesian approach to infer their posteriors. Finally, we implement the variational approach for single image super-resolution (SISR) using deep neural networks, and propose an unsupervised training strategy. The experiments on three image restoration tasks, i.e., ideal SISR, realistic SISR, and real-world SISR, demonstrate that our method has superior model generalizability against varying noise levels and degradation kernels and is effective in unsupervised SISR. The code and resulting models are released via https://zmiclab.github.io/projects.html.

Searching Efficient Model-Guided Deep Network for Image Denoising

Unlike the success of neural architecture search (NAS) in high-level vision tasks, it remains challenging to find computationally efficient and memory-efficient solutions to low-level vision problems such as image restoration through NAS. One of the fundamental barriers to differential NAS-based image restoration is the optimization gap between the super-network and the sub-architectures, causing instability during the searching process. In this paper, we present a novel approach to fill this gap in image denoising application by connecting model-guided design (MoD) with NAS (MoD-NAS). Specifically, we propose to construct a new search space under a model-guided framework and develop more stable and efficient differential search strategies. MoD-NAS employs a highly reusable width search strategy and a densely connected search block to automatically select the operations of each layer as well as network width and depth via gradient descent. During the search process, the proposed MoD-NAS remains stable because of the smoother search space designed under the model-guided framework. Experimental results on several popular datasets show that our MoD-NAS method has achieved at least comparable even better PSNR performance than current state-of-the-art methods with fewer parameters, fewer flops, and less testing time. "The code associate with this paper is available at: https://see.xidian.edu.cn/faculty/wsdong/Projects/Mod-NAS.htm".

NCT:noise-control multi-object tracking

Multi-Object Tracking (MOT) is an important topic in computer vision. Recent MOT methods based on the anchor-free paradigm trade complicated hierarchical structures for tracking performance. However, existing anchor-free MOT methods ignore the noise in detection, data association, and trajectory reconnection stages, which results in serious problems, such as missing detection of small objects, insufficient motion information, and trajectory drifting. To solve these problems, this paper proposes Noise-Control Tracker (NCT), which focuses on the noise-control design of detection, association, and reconnection. First, a prior depth denoise method is introduced to suppress the fusion feature redundant noise, which can recover the gradient information of the heatmap fusion features. Then, the Smoothing Gain Kalman filter is designed, which combines the Gaussian function with the adaptive observation coefficient matrix to stabilize the mutation noise of Kalman gain. Finally, to address the drift noise issue, the gradient boosting reconnection context mechanism is designed, which realizes adaptive trajectory reconnection to effectively fill the gaps in trajectories. With the assistance of the plug-and-play noise-control method, the experimental results on MOTChallenge 16 &17 datasets indicate that the NCT can achieve better performance than other state-of-the-art trackers.

Tensor Cascaded-Rank Minimization in Subspace: A Unified Regime for Hyperspectral Image Low-Level Vision

Low-rank tensor representation philosophy has enjoyed a reputation in many hyperspectral image (HSI) low-level vision applications, but previous studies often failed to comprehensively exploit the low-rank nature of HSI along different modes in low-dimensional subspace, and unsurprisingly handled only one specific task. To address these challenges, in this paper, we figured out that in addition to the spatial correlation, the spectral dependency of HSI also implicitly exists in the coefficient tensor of its subspace, this crucial dependency that was not fully utilized by previous studies yet can be effectively exploited in a cascaded manner. This led us to propose a unified subspace low-rank learning regime with a new tensor cascaded rank minimization, named STCR, to fully couple the low-rankness of HSI in different domains for various low-level vision tasks. Technically, the high-dimensional HSI was first projected into a low-dimensional tensor subspace, then a novel tensor low-cascaded-rank decomposition was designed to collapse the constructed tensor into three core tensors in succession to more thoroughly exploit the correlations in spatial, nonlocal, and spectral modes of the coefficient tensor. Next, difference continuity-regularization was introduced to learn a basis that more closely approximates the HSI's endmembers. The proposed regime realizes a comprehensive delineation of the self-portrait of HSI tensor. Extensive evaluations conducted with dozens of state-of-the-art (SOTA) baselines on eight datasets verified that the proposed regime is highly effective and robust to typical HSI low-level vision tasks, including denoising, compressive sensing reconstruction, inpainting, and destriping. The source code of our method is released at https://github.com/CX-He/STCR.git.

DWDN: Deep Wiener Deconvolution Network for Non-Blind Image Deblurring

We present a simple and effective approach for non-blind image deblurring, combining classical techniques and deep learning. In contrast to existing methods that deblur the image directly in the standard image space, we propose to perform an explicit deconvolution process in a feature space by integrating a classical Wiener deconvolution framework with learned deep features. A multi-scale cascaded feature refinement module then predicts the deblurred image from the deconvolved deep features, progressively recovering detail and small-scale structures. The proposed model is trained in an end-to-end manner and evaluated on scenarios with simulated Gaussian noise, saturated pixels, or JPEG compression artifacts as well as real-world images. Moreover, we present detailed analyses of the benefit of the feature-based Wiener deconvolution and of the multi-scale cascaded feature refinement as well as the robustness of the proposed approach. Our extensive experimental results show that the proposed deep Wiener deconvolution network facilitates deblurred results with visibly fewer artifacts and quantitatively outperforms state-of-the-art non-blind image deblurring methods by a wide margin.

Iterative deep neural networks based on proximal gradient descent for image restoration

The algorithm unfolding networks with explainability of algorithms and higher efficiency of Deep Neural Networks (DNN) have received considerable attention in solving ill-posed inverse problems. Under the algorithm unfolding network framework, we propose a novel end-to-end iterative deep neural network and its fast network for image restoration. The first one is designed making use of proximal gradient descent algorithm of variational models, which consists of denoiser and reconstruction sub-networks. The second one is its accelerated version with momentum factors. For sub-network of denoiser, we embed the Convolutional Block Attention Module (CBAM) in previous U-Net for adaptive feature refinement. Experiments on image denoising and deblurring demonstrate that competitive performances in quality and efficiency are gained by compared with several state-of-the-art networks for image restoration. Proposed unfolding DNN can be easily extended to solve other similar image restoration tasks, such as image super-resolution, image demosaicking, etc.

Video restoration based on deep learning: a comprehensive survey

Video restoration concerns the recovery of a clean video sequence starting from its degraded version. Different video restoration tasks exist, including denoising, deblurring, super-resolution, and reduction of compression artifacts. In this paper, we provide a comprehensive review of the main features of existing video restoration methods based on deep learning. We focus our attention on the main architectural components, strategies for motion handling, and loss functions. We analyze the standard benchmark datasets and use them to summarize the performance of video restoration methods, both in terms of effectiveness and efficiency. In conclusion, the main challenges and future research directions in video restoration using deep learning are highlighted.

Plug-and-Play Regularization Using Linear Solvers

There has been tremendous research on the design of image regularizers over the years, from simple Tikhonov and Laplacian to sophisticated sparsity and CNN-based regularizers. Coupled with a model-based loss function, these are typically used for image reconstruction within an optimization framework. The technical challenge is to develop a regularizer that can accurately model realistic images and be optimized efficiently along with the loss function. Motivated by the recent plug-and-play paradigm for image regularization, we construct a quadratic regularizer whose reconstruction capability is competitive with state-of-the-art regularizers. The novelty of the regularizer is that, unlike classical regularizers, the quadratic objective function is derived from the observed data. Since the regularizer is quadratic, we can reduce the optimization to solving a linear system for applications such as superresolution, deblurring, inpainting, etc. In particular, we show that using iterative Krylov solvers, we can converge to the solution in few iterations, where each iteration requires an application of the forward operator and a linear denoiser. The surprising finding is that we can get close to deep learning methods in terms of reconstruction quality. To the best of our knowledge, the possibility of achieving near state-of-the-art performance using a linear solver is novel.

Deep Spatial-Angular Regularization for Light Field Imaging, Denoising, and Super-Resolution

Coded aperture is a promising approach for capturing the 4-D light field (LF), in which the 4-D data are compressively modulated into 2-D coded measurements that are further decoded by reconstruction algorithms. The bottleneck lies in the reconstruction algorithms, resulting in rather limited reconstruction quality. To tackle this challenge, we propose a novel learning-based framework for the reconstruction of high-quality LFs from acquisitions via learned coded apertures. The proposed method incorporates the measurement observation into the deep learning framework elegantly to avoid relying entirely on data-driven priors for LF reconstruction. Specifically, we first formulate the compressive LF reconstruction as an inverse problem with an implicit regularization term. Then, we construct the regularization term with a deep efficient spatial-angular separable convolutional sub-network in the form of local and global residual learning to comprehensively explore the signal distribution free from the limited representation ability and inefficiency of deterministic mathematical modeling. Furthermore, we extend this pipeline to LF denoising and spatial super-resolution, which could be considered as variants of coded aperture imaging equipped with different degradation matrices. Extensive experimental results demonstrate that the proposed methods outperform state-of-the-art approaches to a significant extent both quantitatively and qualitatively, i.e., the reconstructed LFs not only achieve much higher PSNR/SSIM but also preserve the LF parallax structure better on both real and synthetic LF benchmarks. The code will be publicly available at https://github.com/MantangGuo/DRLF.

Plug-and-Play Image Restoration With Deep Denoiser Prior

Recent works on plug-and-play image restoration have shown that a denoiser can implicitly serve as the image prior for model-based methods to solve many inverse problems. Such a property induces considerable advantages for plug-and-play image restoration (e.g., integrating the flexibility of model-based method and effectiveness of learning-based methods) when the denoiser is discriminatively learned via deep convolutional neural network (CNN) with large modeling capacity. However, while deeper and larger CNN models are rapidly gaining popularity, existing plug-and-play image restoration hinders its performance due to the lack of suitable denoiser prior. In order to push the limits of plug-and-play image restoration, we set up a benchmark deep denoiser prior by training a highly flexible and effective CNN denoiser. We then plug the deep denoiser prior as a modular part into a half quadratic splitting based iterative algorithm to solve various image restoration problems. We, meanwhile, provide a thorough analysis of parameter setting, intermediate results and empirical convergence to better understand the working mechanism. Experimental results on three representative image restoration tasks, including deblurring, super-resolution and demosaicing, demonstrate that the proposed plug-and-play image restoration with deep denoiser prior not only significantly outperforms other state-of-the-art model-based methods but also achieves competitive or even superior performance against state-of-the-art learning-based methods. The source code is available at https://github.com/cszn/DPIR.

Learning Deep Context-Sensitive Decomposition for Low-Light Image Enhancement

Enhancing the quality of low-light (LOL) images plays a very important role in many image processing and multimedia applications. In recent years, a variety of deep learning techniques have been developed to address this challenging task. A typical framework is to simultaneously estimate the illumination and reflectance, but they disregard the scene-level contextual information encapsulated in feature spaces, causing many unfavorable outcomes, e.g., details loss, color unsaturation, and artifacts. To address these issues, we develop a new context-sensitive decomposition network (CSDNet) architecture to exploit the scene-level contextual dependencies on spatial scales. More concretely, we build a two-stream estimation mechanism including reflectance and illumination estimation network. We design a novel context-sensitive decomposition connection to bridge the two-stream mechanism by incorporating the physical principle. The spatially varying illumination guidance is further constructed for achieving the edge-aware smoothness property of the illumination component. According to different training patterns, we construct CSDNet (paired supervision) and context-sensitive decomposition generative adversarial network (CSDGAN) (unpaired supervision) to fully evaluate our designed architecture. We test our method on seven testing benchmarks [including massachusetts institute of technology (MIT)-Adobe FiveK, LOL, ExDark, and naturalness preserved enhancement (NPE)] to conduct plenty of analytical and evaluated experiments. Thanks to our designed context-sensitive decomposition connection, we successfully realized excellent enhanced results (with sufficient details, vivid colors, and few noises), which fully indicates our superiority against existing state-of-the-art approaches. Finally, considering the practical needs for high efficiency, we develop a lightweight CSDNet (named LiteCSDNet) by reducing the number of channels. Furthermore, by sharing an encoder for these two components, we obtain a more lightweight version (SLiteCSDNet for short). SLiteCSDNet just contains 0.0301M parameters but achieves the almost same performance as CSDNet. Code is available at https://github.com/KarelZhang/CSDNet-CSDGAN.

Nonblind Image Deblurring via Deep Learning in Complex Field

Nonblind image deblurring is about recovering the latent clear image from a blurry one generated by a known blur kernel, which is an often-seen yet challenging inverse problem in imaging. Its key is how to robustly suppress noise magnification during the inversion process. Recent approaches made a breakthrough by exploiting convolutional neural network (CNN)-based denoising priors in the image domain or the gradient domain, which allows using a CNN for noise suppression. The performance of these approaches is highly dependent on the effectiveness of the denoising CNN in removing magnified noise whose distribution is unknown and varies at different iterations of the deblurring process for different images. In this article, we introduce a CNN-based image prior defined in the Gabor domain. The prior not only utilizes the optimal space-frequency resolution and strong orientation selectivity of the Gabor transform but also enables using complex-valued (CV) representations in intermediate processing for better denoising. A CV CNN is developed to exploit the benefits of the CV representations, with better generalization to handle unknown noises over the real-valued ones. Combining our Gabor-domain CV CNN-based prior with an unrolling scheme, we propose a deep-learning-based approach to nonblind image deblurring. Extensive experiments have demonstrated the superior performance of the proposed approach over the state-of-the-art ones.

Spectral Response Function-Guided Deep Optimization-Driven Network for Spectral Super-Resolution

Hyperspectral images (HSIs) are crucial for many research works. Spectral super-resolution (SSR) is a method used to obtain high-spatial-resolution (HR) HSIs from HR multispectral images. Traditional SSR methods include model-driven algorithms and deep learning. By unfolding a variational method, this article proposes an optimization-driven convolutional neural network (CNN) with a deep spatial-spectral prior, resulting in physically interpretable networks. Unlike the fully data-driven CNN, auxiliary spectral response function (SRF) is utilized to guide CNNs to group the bands with spectral relevance. In addition, the channel attention module (CAM) and the reformulated spectral angle mapper loss function are applied to achieve an effective reconstruction model. Finally, experiments on two types of data sets, including natural and remote sensing images, demonstrate the spectral enhancement effect of the proposed method, and also, the classification results on the remote sensing data set verified the validity of the information enhanced by the proposed method.

MoG-DS: model-guided deep convolutional network for joint denoising and super-resolution of a single-photon counting image

Single-photon counting (SPC) imaging has attracted considerable research attention in recent years due to its capability to detect targets under extremely low-light conditions. However, the spatial quality of SPC images is always unsatisfactory because they typically suffer from considerable effects of noise and their spatial resolution is low. Most traditional methods are dedicated to solving the noise problem while ignoring the improvement of spatial resolution. To address these challenging issues, we propose a novel model-guided deep convolutional network for joint denoising and super-resolution (SR) of SPC images. First, we introduce a model-based iterative optimization algorithm with deep regularizer to unify denoising and SR into one problem. Second, we construct a model-guided deep convolutional network by unfolding the aforementioned model-based iterative algorithm to achieve an optimal solution. All modules in the proposed network are interpretable due to the special model-guided design, and they enable good generalization in real situations. In addition, the deep regularizer and other parameters in the proposed network are jointly optimized in an end-to-end manner, which efficiently reduces the difficulty of parameter design. Extensive simulation and real experimental results are reported to demonstrate the superiority of the proposed method in terms of visual comparison and quantitative analysis, respectively.

Content-Aware Scalable Deep Compressed Sensing

To more efficiently address image compressed sensing (CS) problems, we present a novel content-aware scalable network dubbed CASNet which collectively achieves adaptive sampling rate allocation, fine granular scalability and high-quality reconstruction. We first adopt a data-driven saliency detector to evaluate the importance of different image regions and propose a saliency-based block ratio aggregation (BRA) strategy for sampling rate allocation. A unified learnable generating matrix is then developed to produce sampling matrix of any CS ratio with an ordered structure. Being equipped with the optimization-inspired recovery subnet guided by saliency information and a multi-block training scheme preventing blocking artifacts, CASNet jointly reconstructs the image blocks sampled at various sampling rates with one single model. To accelerate training convergence and improve network robustness, we propose an SVD-based initialization scheme and a random transformation enhancement (RTE) strategy, which are extensible without introducing extra parameters. All the CASNet components can be combined and learned end-to-end. We further provide a four-stage implementation for evaluation and practical deployments. Experiments demonstrate that CASNet outperforms other CS networks by a large margin, validating the collaboration and mutual supports among its components and strategies. Codes are available at https://github.com/Guaishou74851/CASNet.

Spatial and Spectral-Channel Attention Network for Denoising on Hyperspectral Remote Sensing Image

Hyperspectral images (HSIs) are frequently contaminated by different noises (Gaussian noise, stripe noise, deadline noise, impulse noise) in the acquisition process as a result of the observation environment and imaging system limitations, which makes image information lost and difficult to recover. In this paper, we adopt a 3D-based SSCA block neural network of U-Net architecture for remote sensing HSI denoising, named SSCANet (Spatial and Spectral-Channel Attention Network), which is mainly constructed by a so-called SSCA block. By fully considering the characteristics of spatial-domain and spectral-domain of remote sensing HSIs, the SSCA block consists of a spatial attention (SA) block and a spectral-channel attention (SCA) block, in which the SA block is to extract spatial information and enhance spatial representation ability, as well as the SCA block to explore the band-wise relationship within HSIs for preserving spectral information. Compared to earlier 2D convolution, 3D convolution has a powerful spectrum preservation ability, allowing for improved extraction of HSIs characteristics. Experimental results demonstrate that our method holds better-restored results than other compared approaches, both visually and quantitatively.

Non-blind optical degradation correction via frequency self-adaptive and finetune tactics

In mobile photography applications, limited volume constraints the diversity of optical design. In addition to the narrow space, the deviations introduced in mass production cause random bias to the real camera. In consequence, these factors introduce spatially varying aberration and stochastic degradation into the physical formation of an image. Many existing methods obtain excellent performance on one specific device but are not able to quickly adapt to mass production. To address this issue, we propose a frequency self-adaptive model to restore realistic features of the latent image. The restoration is mainly performed in the Fourier domain and two attention mechanisms are introduced to match the feature between Fourier and spatial domain. Our method applies a lightweight network, without requiring modification when the fields of view (FoV) changes. Considering the manufacturing deviations of a specific camera, we first pre-train a simulation-based model, then finetune it with additional manufacturing error, which greatly decreases the time and computational overhead consumption in implementation. Extensive results verify the promising applications of our technique for being integrated with the existing post-processing systems.

Rank-One Network: An Effective Framework for Image Restoration

The principal rank-one (RO) components of an image represent the self-similarity of the image, which is an important property for image restoration. However, the RO components of a corrupted image could be decimated by the procedure of image denoising. We suggest that the RO property should be utilized and the decimation should be avoided in image restoration. To achieve this, we propose a new framework comprised of two modules, i.e., the RO decomposition and RO reconstruction. The RO decomposition is developed to decompose a corrupted image into the RO components and residual. This is achieved by successively applying RO projections to the image or its residuals to extract the RO components. The RO projections, based on neural networks, extract the closest RO component of an image. The RO reconstruction is aimed to reconstruct the important information, respectively from the RO components and residual, as well as to restore the image from this reconstructed information. Experimental results on four tasks, i.e., noise-free image super-resolution (SR), realistic image SR, gray-scale image denoising, and color image denoising, show that the method is effective and efficient for image restoration, and it delivers superior performance for realistic image SR and color image denoising. Our source code is available online.

DHNet: High-resolution and hierarchical network for cross-domain oct speckle noise reduction

PURPOSE

Optical coherence tomography (OCT) imaging uses the principle of Michelson interferometry to obtain high-resolution images by coherent superposing of multiple forward and backward scattered light waves with random phases. This process inevitably produces speckle noise that severely compromises visual quality of OCT images and degrades performances of subsequent image analysis tasks. In addition, datasets obtained by different OCT scanners have distribution shifts, making a speckle noise suppression model difficult to be generalized across multiple datasets. In order to solve the above issues, we propose a novel end-to-end denoising framework for OCT images collected by different scanners.

METHODS

The proposed model utilizes the high-resolution network (HRNet) as backbone for image restoration, which reconstructs high fidelity images by maintaining high-resolution representations throughout the entire learning process. To compensate distribution shifts among datasets collected by different scanners, we develop a hierarchical adversarial learning strategy for domain adaption. The proposed model is trained using datasets with clean ground truth produced by two commercial OCT scanners, and then applied to suppress speckle noise in OCT images collected by our recently developed OCT scanner, BV-1000 (China Bigvision Corporation). We name the proposed model as DHNet (Double-H-Net, High-resolution and Hierarchical Network).

RESULTS

We compare DHNet with state-of-the-art methods and experiment results show that DHNet improves signal-to-noise ratio (SNR) by a large margin of 18.137dB as compared to the best of our previous method. In addition, DHNet achieves a testing time of 25ms, which satisfies the real-time processing requirement for the BV-1000 scanner. We also conduct retinal layer segmentation experiment on OCT images before and after denoising and show that DHNet can also improve segmentation.

CONCLUSIONS

The proposed DHNet can compensate domain shifts between different datasets while significantly improve speckle noise suppression. The HRNet backbone is utilized to carry low- and high-resolution information to recover fidelity images. Domain adaptation is achieved by a hierarchical module through adversarial learning. In addition, DHNet achieved a testing time of 25ms, which satisfied the real-time processing requirement. This article is protected by copyright. All rights reserved.

Multi-Color Channels Based Group Sparse Model for Image Restoration

The group sparse representation (GSR) model combines local sparsity and nonlocal similarity in image processing, and achieves excellent results. However, the traditional GSR model and all subsequent improved GSR models convert the RGB space of the image to YCbCr space, and only extract the Y (luminance) channel of YCbCr space to change the color image to a gray image for processing. As a result, the image processing process cannot be loyal to each color channel, so the repair effect is not ideal. A new group sparse representation model based on multi-color channels is proposed in this paper. The model processes R, G and B color channels simultaneously when processing color images rather than processing a single color channel and then combining the results of different channels. The proposed multi-color-channels-based GSR model is compared with state-of-the-art methods. The experimental contrast results show that the proposed model is an effective method and can obtain good results in terms of objective quantitative metrics and subjective visual effects.

An efficient residual learning deep convolutional neural network for de-noising medical images

Image denoising is a pre-processing technique that is done in every image processing applications.  It plays a significant role in the performance of any methods.  The objective of this paper is to remove Gaussian noises at different noise levels in medical images.  This paper proposed an efficient Deep Convolution Neural Network model for denoising medical images to remove Gaussian noise using Residual Learning.  Convolutional Neural Networks  are a class of deep neural networks that can be trained on large databases and have excellent performance on image denoising.  Residual learning and batch normalisation are various techniques used to enhance the training process and denoising performance. The proposed RL-DCNN method is tested with 20 layers and evaluated using the performance metrics Peak Signal to Noise Ratio, Mean Square Error  and Structural Similarity.   It is compared with Denoising Convolutional Neural Network and Shrinkage Convolutional Neural Network models and proved to be better than the other methods.

Multi-Task Interaction Learning for Spatiospectral Image Super-Resolution

High spatial resolution and high spectral resolution images (HR-HSIs) are widely applied in geosciences, medical diagnosis, and beyond. However, how to get images with both high spatial resolution and high spectral resolution is still a problem to be solved. In this paper, we present a deep spatial-spectral feature interaction network (SSFIN) for reconstructing an HR-HSI from a low-resolution multispectral image (LR-MSI), e.g., RGB image. In particular, we introduce two auxiliary tasks, i.e., spatial super-resolution (SR) and spectral SR to help the network recover the HR-HSI better. Since higher spatial resolution can provide more detailed information about image texture and structure, and richer spectrum can provide more attribute information, we propose a spatial-spectral feature interaction block (SSFIB) to make the spatial SR task and the spectral SR task benefit each other. Therefore, we can make full use of the rich spatial and spectral information extracted from the spatial SR task and spectral SR task, respectively. Moreover, we use a weight decay strategy (for the spatial and spectral SR tasks) to train the SSFIN, so that the model can gradually shift attention from the auxiliary tasks to the primary task. Both quantitative and visual results on three widely used HSI datasets demonstrate that the proposed method achieves a considerable gain compared to other state-of-the-art methods. Source code is available at https://github.com/junjun-jiang/SSFIN.

MHF-Net: An Interpretable Deep Network for Multispectral and Hyperspectral Image Fusion

Multispectral and hyperspectral image fusion (MS/HS fusion) aims to fuse a high-resolution multispectral (HrMS) and a low-resolution hyperspectral (LrHS) images to generate a high-resolution hyperspectral (HrHS) image, which has become one of the most commonly addressed problems for hyperspectral image processing. In this paper, we specifically designed a network architecture for the MS/HS fusion task, called MHF-net, which not only contains clear interpretability, but also reasonably embeds the well studied linear mapping that links the HrHS image to HrMS and LrHS images. In particular, we first construct an MS/HS fusion model which merges the generalization models of low-resolution images and the low-rankness prior knowledge of HrHS image into a concise formulation, and then we build the proposed network by unfolding the proximal gradient algorithm for solving the proposed model. As a result of the careful design for the model and algorithm, all the fundamental modules in MHF-net have clear physical meanings and are thus easily interpretable. This not only greatly facilitates an easy intuitive observation and analysis on what happens inside the network, but also leads to its good generalization capability. Based on the architecture of MHF-net, we further design two deep learning regimes for two general cases in practice: consistent MHF-net and blind MHF-net. The former is suitable in the case that spectral and spatial responses of training and testing data are consistent, just as considered in most of the pervious general supervised MS/HS fusion researches. The latter ensures a good generalization in mismatch cases of spectral and spatial responses in training and testing data, and even across different sensors, which is generally considered to be a challenging issue for general supervised MS/HS fusion methods. Experimental results on simulated and real data substantiate the superiority of our method both visually and quantitatively as compared with state-of-the-art methods along this line of research.