Enhanced deep unrolling networks for snapshot compressive hyperspectral imaging.

Snapshot compressive hyperspectral imaging necessitates the reconstruction of a complete hyperspectral image from its compressive snapshot measurement, presenting a challenging inverse problem. This paper proposes an enhanced deep unrolling neural network, called EDUNet, to tackle this problem. The EDUNet is constructed via the deep unrolling of a proximal gradient descent algorithm and introduces two innovative modules for gradient-driven update and proximal mapping reflectivity. The gradient-driven update module leverages a memory-assistant descent approach inspired by momentum-based acceleration techniques, for enhancing the unrolled reconstruction process and improving convergence. The proximal mapping is modeled by a sub-network with a cross-stage spectral self-attention, which effectively exploits the inherent self-similarities present in hyperspectral images along the spectral axis. It also enhances feature flow throughout the network, contributing to reconstruction performance gain. Furthermore, we introduce a spectral geometry consistency loss, encouraging EDUNet to prioritize the geometric layouts of spectral curves, leading to a more precise capture of spectral information in hyperspectral images. Experiments are conducted using three benchmark datasets including KAIST, ICVL, and Harvard, along with some real data, comprising a total of 73 samples. The experimental results demonstrate that EDUNet outperforms 15 competing models across four metrics including PSNR, SSIM, SAM, and ERGAS.

Siamese Cooperative Learning for Unsupervised Image Reconstruction from Incomplete Measurements.

Image reconstruction from incomplete measurements is one basic task in imaging. While supervised deep learning has emerged as a powerful tool for image reconstruction in recent years, its applicability is limited by its prerequisite on a large number of latent images for model training. To extend the application of deep learning to the imaging tasks where acquisition of latent images is challenging, this paper proposes an unsupervised deep learning method that trains a deep model for image reconstruction with the access limited to measurement data. We develop a Siamese network whose twin sub-networks perform reconstruction cooperatively on a pair of complementary spaces: the null space of the measurement matrix and the range space of its pseudo inverse. The Siamese network is trained by a self-supervised loss with three terms: a data consistency loss over available measurements in the range space, a data consistency loss between intermediate results in the null space, and a mutual consistency loss on the predictions of the twin sub-networks in the full space. The proposed method is applied to four imaging tasks from different applications, and extensive experiments have shown its advantages over existing unsupervised solutions.

Salting-Out Effect Realizing High-Strength and Dendrite-Inhibiting Cellulose Hydrogel Electrolyte for Durable Aqueous Zinc-Ion Batteries.

Aqueous zinc-ion batteries are limited by poor Zn stripping/plating reversibility. Not only can hydrogel electrolytes address this issue, but also they are suitable for constructing flexible batteries. However, there exists a contradiction between the mechanical strength and the ionic conductivity for hydrogel electrolytes. Herein, high-concentration kosmotropic ions are introduced into the cellulose hydrogel electrolyte to take advantage of the salting-out effect. This can significantly improve both the mechanical strength and ionic conductivity. Additionally, the obtained cellulose hydrogel electrolyte (denoted as Con-CMC) has strong adhesion, a wide electrochemical stability window, and good water retaining ability. The Con-CMC is also found to accelerate the desolvation process, improve Zn deposition kinetics, promote Zn deposition along the (002) plane, and suppress parasitic reactions. Accordingly, the Zn/Zn cell with Con-CMC demonstrates dendrite-free behavior with prolonged lifespan and can endure extremely large areal capacity of 25 mAh cm-2. The Con-CMC also enables a large average Coulombic efficiency of 99.54% over 500 cycles for the Zn/Cu cell. Furthermore, the assembled pouch-type Zn/polyaniline full battery provides great rate capability, superior cyclability (even with limited Zn anode excess), a slow self-discharge rate, and outstanding affordability to external forces. Overall, this work extends our knowledge of the rational design of hydrogel electrolytes.

Facile and green synthesis of nanocellulose with the assistance of ultraviolet light irradiation for high-performance quasi-solid-state zinc-ion batteries.

Benefiting from excellent mechanical properties, large surface area, rich hydroxyl groups, good sustainability, etc., nanocellulose is highly promising for various applications. However, intense chemical treatment and long-term processing are usually required to fabricate nanocellulose. Herein, a new synthesis method of nanocellulose is developed by using ultraviolet light irradiation-assisted delignification and subsequent sonification. This method is more cost-effective, time-saving, and environmentally benign compared to most of previously reported synthesis methods of nanocellulose. The obtained nanocellulose contains a small amount of lignin, which is unfavorable for high-temperature stability and optimal transparency. However, a small amount of lignin is beneficial to mechanical properties and in-water stability. With this nanocellulose, flexible MnO2 cathode film and hydrogel electrolyte are constructed and a quasi-solid-state zinc-ion battery is assembled. The battery exhibits 233.3 mAh g-1 after 1000 cycles at 1 A g-1 and 20 ℃. And more than half of that capacity can be maintained at -20 ℃. The battery also possesses great rate capability and good endurance to external forces. This work provides new insights into the synthesis and application of nanocellulose.

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.

Multi-View 3D Shape Recognition via Correspondence-Aware Deep Learning.

In recent years, multi-view learning has emerged as a promising approach for 3D shape recognition, which identifies a 3D shape based on its 2D views taken from different viewpoints. Usually, the correspondences inside a view or across different views encode the spatial arrangement of object parts and the symmetry of the object, which provide useful geometric cues for recognition. However, such view correspondences have not been explicitly and fully exploited in existing work. In this paper, we propose a correspondence-aware representation (CAR) module, which explicitly finds potential intra-view correspondences and cross-view correspondences via k NN search in semantic space and then aggregates the shape features from the correspondences via learned transforms. Particularly, the spatial relations of correspondences in terms of their viewpoint positions and intra-view locations are taken into account for learning correspondence-aware features. Incorporating the CAR module into a ResNet-18 backbone, we propose an effective deep model called CAR-Net for 3D shape classification and retrieval. Extensive experiments have demonstrated the effectiveness of the CAR module as well as the excellent performance of the CAR-Net.

Watermarking Deep Neural Networks in Image Processing.

Publishing/sharing pretrained deep neural network (DNN) models is a common practice in the community of computer vision. The increasing popularity of pretrained models has made it a serious concern: how to protect the intellectual properties of model owners and avert illegal usages by malicious attackers. This article aims at developing a framework for watermarking DNNs, with a particular focus on low-level image processing tasks that map images to images. Using image denoising and superresolution as case studies, we develop a black-box watermarking method for pretrained models, which exploits the overparameterization of the DNNs in image processing. In addition, an auxiliary module for visualizing the watermark information is proposed for further verification. Extensive experiments show that the proposed watermarking framework has no noticeable impact on model performance and enjoys the robustness against the often-seen attacks.

Structure-Texture Image Decomposition Using Discriminative Patch Recurrence.

Morphology component analysis provides an effective framework for structure-texture image decomposition, which characterizes the structure and texture components by sparsifying them with certain transforms respectively. Due to the complexity and randomness of texture, it is challenging to design effective sparsifying transforms for texture components. This paper aims at exploiting the recurrence of texture patterns, one important property of texture, to develop a nonlocal transform for texture component sparsification. Since the plain patch recurrence holds for both cartoon contours and texture regions, the nonlocal sparsifying transform constructed based on such patch recurrence sparsifies both the structure and texture components well. As a result, cartoon contours could be wrongly assigned to the texture component, yielding ambiguity in decomposition. To address this issue, we introduce a discriminative prior on patch recurrence, that the spatial arrangement of recurrent patches in texture regions exhibits isotropic structure which differs from that of cartoon contours. Based on the prior, a nonlocal transform is constructed which only sparsifies texture regions well. Incorporating the constructed transform into morphology component analysis, we propose an effective approach for structure-texture decomposition. Extensive experiments have demonstrated the superior performance of our approach over existing ones.

Dielectric constant of supercritical water in a large pressure-temperature range.

A huge amount of water at supercritical conditions exists in Earth's interior, where its dielectric properties play a critical role in determining how it stores and transports materials. However, it is very challenging to obtain the static dielectric constant of water, ϵ0, in a wide pressure-temperature (P-T) range as found in deep Earth either experimentally or by first-principles simulations. Here, we introduce a neural network dipole model, which, combined with molecular dynamics, can be used to compute P-T dependent dielectric properties of water as accurately as first-principles methods but much more efficiently. We found that ϵ0 may vary by one order of magnitude in Earth's upper mantle, suggesting that the solvation properties of water change dramatically at different depths. Although ϵ0 and the molecular dipole moment increase with an increase in pressure along an isotherm, the dipolar angular correlation has its maximum at 5 GPa-7 GPa, which may indicate that hydrogen bonds become weaker at high pressure. We also calculated the frequency-dependent dielectric constant of water in the microwave range, which, to the best of our knowledge, has not been calculated from first principles, and found that temperature affects the dielectric absorption more than pressure. Our results are of great use in many areas, e.g., modeling water-rock interactions in geochemistry. The computational approach introduced here can be readily applied to other molecular fluids.

High-Performance Anti-freezing Flexible Zn-MnO2 Battery Based on Polyacrylamide/Graphene Oxide/Ethylene Glycol Gel Electrolyte.

It remains a great challenge for aqueous zinc-ion batteries to work at subzero temperatures, since the water in aqueous electrolytes would freeze and inhibit the transportation of electrolyte ions, inevitably leading to performance deterioration. In this work, we propose an anti-freezing gel electrolyte that contains polyacrylamide, graphene oxide, and ethylene glycol. The graphene oxide can not only enhance the mechanical properties of gel electrolyte but also help construct a three-dimensional macroporous network that facilitates ionic transport, while the ethylene glycol can improve freezing resistance. Due to the synergistic effect, the gel electrolyte exhibits high ionic conductivity (e.g., 14.9 mS cm-1 at -20 °C) and good mechanical properties in comparison with neat polyacrylamide gel electrolyte. Benefiting from that, the assembled flexible quasi-solid-state Zn-MnO2 battery exhibits good electrochemical durability and superior tolerance to extreme working conditions. This work provides new perspectives to develop flexible electrochemical energy storage devices with great environmental adaptability.

Advancing Image Understanding in Poor Visibility Environments: A Collective Benchmark Study.

Existing enhancement methods are empirically expected to help the high-level end computer vision task: however, that is observed to not always be the case in practice. We focus on object or face detection in poor visibility enhancements caused by bad weathers (haze, rain) and low light conditions. To provide a more thorough examination and fair comparison, we introduce three benchmark sets collected in real-world hazy, rainy, and low-light conditions, respectively, with annotated objects/faces. We launched the UG2+ challenge Track 2 competition in IEEE CVPR 2019, aiming to evoke a comprehensive discussion and exploration about whether and how low-level vision techniques can benefit the high-level automatic visual recognition in various scenarios. To our best knowledge, this is the first and currently largest effort of its kind. Baseline results by cascading existing enhancement and detection models are reported, indicating the highly challenging nature of our new data as well as the large room for further technical innovations. Thanks to a large participation from the research community, we are able to analyze representative team solutions, striving to better identify the strengths and limitations of existing mindsets as well as the future directions.

Image Denoising via Sequential Ensemble Learning.

Image denoising is about removing measurement noise from input image for better signal-to-noise ratio. In recent years, there has been great progress on the development of data-driven approaches for image denoising, which introduce various techniques and paradigms from machine learning in the design of image denoisers. This paper aims at investigating the application of ensemble learning in image denoising, which combines a set of simple base denoisers to form a more effective image denoiser. Based on different types of image priors, two types of base denoisers in the form of transform-shrinkage are proposed for constructing the ensemble. Then, with an effective re-sampling scheme, several ensemble-learning-based image denoisers are constructed using different sequential combinations of multiple proposed base denoisers. The experiments showed that sequential ensemble learning can effectively boost the performance of image denoising.

Exploiting Global Low-Rank Structure and Local Sparsity Nature for Tensor Completion.

In the era of data science, a huge amount of data has emerged in the form of tensors. In many applications, the collected tensor data are incomplete with missing entries, which affects the analysis process. In this paper, we investigate a new method for tensor completion, in which a low-rank tensor approximation is used to exploit the global structure of data, and sparse coding is used for elucidating the local patterns of data. Regarding the characterization of low-rank structures, a weighted nuclear norm for the tensor is introduced. Meanwhile, an orthogonal dictionary learning process is incorporated into sparse coding for more effective discovery of the local details of data. By simultaneously using the global patterns and local cues, the proposed method can effectively and efficiently recover the lost information of incomplete tensor data. The capability of the proposed method is demonstrated with several experiments on recovering MRI data and visual data, and the experimental results have shown the excellent performance of the proposed method in comparison with recent related methods.

Dictionary Learning for Sparse Coding: Algorithms and Convergence Analysis.

In recent years, sparse coding has been widely used in many applications ranging from image processing to pattern recognition. Most existing sparse coding based applications require solving a class of challenging non-smooth and non-convex optimization problems. Despite the fact that many numerical methods have been developed for solving these problems, it remains an open problem to find a numerical method which is not only empirically fast, but also has mathematically guaranteed strong convergence. In this paper, we propose an alternating iteration scheme for solving such problems. A rigorous convergence analysis shows that the proposed method satisfies the global convergence property: the whole sequence of iterates is convergent and converges to a critical point. Besides the theoretical soundness, the practical benefit of the proposed method is validated in applications including image restoration and recognition. Experiments show that the proposed method achieves similar results with less computation when compared to widely used methods such as K-SVD.

Fractal analysis for reduced reference image quality assessment.

In this paper, multifractal analysis is adapted to reduced-reference image quality assessment (RR-IQA). A novel RR-QA approach is proposed, which measures the difference of spatial arrangement between the reference image and the distorted image in terms of spatial regularity measured by fractal dimension. An image is first expressed in Log-Gabor domain. Then, fractal dimensions are computed on each Log-Gabor subband and concatenated as a feature vector. Finally, the extracted features are pooled as the quality score of the distorted image using l1 distance. Compared with existing approaches, the proposed method measures image quality from the perspective of the spatial distribution of image patterns. The proposed method was evaluated on seven public benchmark data sets. Experimental results have demonstrated the excellent performance of the proposed method in comparison with state-of-the-art approaches.