Hyperspectral image (HSI) is applicable in many fields due to the ability in discriminating different materials. Collecting HSI usually requires expensive hardware and long period. Reconstructing HSI from RGB image, also called spectral super-resolution (SSR), is an affordable and feasible way for HSI acquisition. Despite the SSR results achieved by existing deep unfolding networks (DUNs), they still face challenges in: 1) recovering the fine-grained and realistic details; 2) suppressing the spectral distortion. Diffusion model has advantages in generating diverse and realistic contents, while its fidelity is limited due to the inherent randomness. In this study, to reconstruct a faithful and realistic HSI, we integrate the diffusion model in DUN, and propose a degradation-aware unrolling diffusion model for SSR (deDiff-SSR). The generative diffusion prior is jointly leveraged with the spectral degradation and deep prior learning. Specifically, we first pre-train a channel attention enhanced denoising diffusion probabilistic model (DDPM), the spectral correlation is exploited for learning the diffusion prior of HSI. To aware the degradation, by optimizing a diffusion and deep priors regularized HSI SSR model, we propose a degradation-aware diffusion sampling method, the spectral degradation is learned to refine each diffusion sampling step. Via unrolling the degradation-aware diffusion sampling steps, we build the deDiff-SSR network. It contains diffusion and deep proximal operators to represent the diffusion and deep priors, respectively. We implement the diffusion proximal operator with one sampling step of the pre-trained DDPM. Moreover, we design a state-space Transformer as the deep proximal operator, the spectral-spatial long-range relationship of HSI can be efficiently captured. The experiments on several indoor and remote sensing datasets demonstrate the effectiveness of deDiff-SSR.

Fluorescence molecular tomography (FMT), particularly within the second near-infrared window (NIR-II, 1000-1700 nm), is a sophisticated imaging technique for numerous medical applications, enabling reconstruction of the three-dimensional (3D) distribution of internal tumors from surface fluorescence signals. Recent studies have demonstrated the effectiveness of deep learning methods in FMT reconstruction tasks, however, their performance heavily relies on large-scale, diverse labeled datasets. The existing researches primarily focused on datasets with static tumor characteristics, including fixed tumor numbers, locations, and sizes, which shows an insufficient pattern diversity, limiting neural networks' generalization ability for complex real-world scenarios beyond the training dataset. To address this limitation, we draw inspiration from the similarity between Monte Carlo photon simulation and sampling process of diffusion model, to propose a diffusion model-based data augmentation strategy. Further, we introduce a novel NIR-II-specific guidance mechanism to enhance sample fidelity and diversity by incorporating NIR-II spectral optical properties. Quantitative analysis validated that high-quality NIR-II fluorescence signal samples are synthesized, where the proposed NIR-II guidance achieved a 56.7% reduction in Fréchet Inception Distance(FID) and a 21.5% improvement in Inception Score (IS), covering a broad spectrum of patterns. Since the synthetic samples are unlabeled which cannot be used for neural network training, these samples are integrated with the original dataset as augmented samples and train FMT neural networks by semi-supervised learning. By combining pattern-diversifying strengths of diffusion models with semi-supervised learning, the proposed strategy maximizes the utility of limited datasets. Both simulative and in vivo experiments confirmed that data augmentation significantly enhances the network's reconstruction performance in precisely localizing tumor sources and reconstructing complex morphologies. Source code release: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/Hermes-HQS/DANG</uri>.

Secondary electron (SE) imaging techniques, such as scanning electron microscopy and helium ion microscopy (HIM), use electrons emitted by a sample in response to a focused beam of charged particles incident at a grid of raster scan positions. Spot size—the diameter of the incident beam's spatial profile—is one of the limiting factors for resolution, along with various sources of noise in the SE signal. The effect of the beam spatial profile is commonly understood as convolutional. We show that under a simple and plausible physical abstraction for the beam, though convolution describes the mean of the SE counts, the full distribution of SE counts is a mixture. We demonstrate that this more detailed modeling can enable resolution improvements over conventional estimators through a stylized application inspired by semiconductor inspection: localizing the edge in a two-valued sample. We derive Fisher information about edge location in conventional and time-resolved measurements (TRM) and also derive the maximum likelihood estimate (MLE) from the latter. Empirically, the MLE computed from TRM is approximately efficient except at very low beam diameter, so Fisher information comparisons are predictive of performance and can be used to optimize the beam diameter relative to the raster scan spacing. Monte Carlo simulations provide an example of the MLE giving a 5-fold reduction in root mean-squared error (RMSE) of edge localization as compared to conventional interpolation-based estimation. The RMSE is substantially below both the beam diameter and the raster scan spacing and thus sub-pixel localization is demonstrated. Applied to three real HIM datasets, the average RMSE reduction factor is 5.4.

The fusion of high spatial resolution multispectral images (HR-MSIs) and low spatial resolution hyperspectral images (LR-HSIs) has been recognized as an effective method for HSI super-resolution (HSI-SR). However, both HSIs and MSIs can be captured under low-light conditions (e.g., nighttime); yet, most existing methods do not explicitly consider modeling brightness variations, which hinders generalization and results in the loss of detailed information in the fused results. To overcome this challenge, we propose an Unfolding Degradation Aware Transformer (UDAT), by decomposing the observed HSI into the element-wise product of a clean component and an illumination degradation component, which are then inferred/estimated through an unfolding framework. Specifically, by leveraging the estimated illumination degradation components to suppress the color bias effect in low-light environments, the proposed UDAT effectively achieves accurate spectral reconstruction and enhanced perceptual quality, thereby significantly improving its adaptability under diverse illumination variations. Due to the lack of any open low-light HSI-SR dataset, we also establish a real low-light HSI-SR dataset, comprising paired low-light and normal-light HSIs and MSIs, to facilitate the comprehensive evaluation of the proposed UDAT. Extensive experiments show that UDAT outperforms state-of-the-art HSI-SR methods in both quantitative assessment and visual quality.

Model-based reconstruction plays a key role in compressed sensing (CS) MRI, as it incorporates effective image regularizers to improve the quality of reconstruction. The Plug-and-Play and Regularization-by-Denoising frameworks leverage advanced denoisers (e.g., convolutional neural network (CNN)-based denoisers) and have demonstrated strong empirical performance. However, their theoretical guarantees remain limited, as practical CNNs often violate key assumptions. In contrast, gradient-driven denoisers achieve competitive performance, and the required assumptions for theoretical analysis are easily satisfied. However, solving the associated optimization problem remains computationally demanding. To address this challenge, we propose a generalized Krylov subspace method (GKSM) to solve the optimization problem efficiently. Moreover, we also establish rigorous convergence guarantees for GKSM in nonconvex settings. Numerical experiments on CS MRI reconstruction with spiral and radial acquisitions validate both the computational efficiency of GKSM and the accuracy of the theoretical predictions. The proposed optimization method is applicable to any linear inverse problem.

With the rapid development of micro/nano technology, the requirements for high-resolution images have become increasingly stringent. However, conventional microscopic imaging suffers from information degradation and irreversible sub-pixel detail loss, which fundamentally limits image quality improvement. To address this issue, this study designs a super resolution reconstruction system based on precision motion modulation and proposes a generative adversarial network (GAN) reconstruction algorithm incorporating variable sequence fusion and attention mechanisms to achieve super-resolution imaging. The proposed system implements a novel computational microscopy framework employing multi-spatial-view sampling, where a sliding-window-inspired acquisition strategy enables the systematic recovery of sub-pixel-scale image information that would otherwise be lost in conventional imaging. Subsequently, the GAN-based algorithm reconstructs high-resolution images. Experimental results demonstrate that the system effectively extends the sub-pixel information of the original image without modifying the existing optical-physical system. It enhances the model's reconstruction capability in terms of texture details and sharpness, significantly improving the overall quality of microscopic reconstructed images, and highlights the advantage of the algorithm in measurement accuracy.

In this paper a system for a mobile device to generate a wide color gamut image is proposed. A RGB camera on a smartphone is combined with a multispectral image sensor, which is fabricated on top of a complementary metal-oxide semiconductor image sensor for a mobile device, capturing scenes with 16 spectral bands. Images from these sensors are fused using a color transfer technique to leverage the accurate color reproduction capability of the multispectral image sensor while preserving the image structures in the RGB image. It is claimed that the proposed multispectral image sensor improved color reproduction accuracy by 25% compared to a mobile RGB sensor, and the proposed system effectively produce a high-resolution wide color gamut image with high color fidelity.

Coded aperture snapshot spectral imaging (CASSI) systems compressively project 3D hyperspectral data onto 2D measurements, offering high imaging speed and data efficiency. However, existing CASSI reconstruction algorithms still suffer from suboptimal reconstruction quality due to the ill-posed nature of hyperspectral compressive sensing reconstruction, which demands effective prior modeling. This paper proposes a novel reconstruction framework that integrates multiple complementary priors, jointly modeling spectral low-rankness, spatial nonlocal self-similarity, and deep image priors to comprehensively capture the intrinsic structure of hyperspectral images across spectral and spatial domains. By combining the strengths of model-based and data-driven priors, the proposed method achieves both strong generalization and expressive capacity. To tackle the optimization challenges posed by multiple regularization terms and parameters, an efficient ADMM-based solver is developed, which decomposes the problem into subproblems with closed-form solutions or those solvable via plug-and-play denoisers. In addition, an adaptive noise estimation mechanism is introduced to automatically tune the regularization parameters, eliminating the need for manual parameter adjustment. Extensive experiments demonstrate that the proposed method consistently outperforms state-of-the-art approaches in terms of reconstruction accuracy and robustness across multiple datasets. Our code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/ETHAN-YA/PnP-Hybrid.git</uri>.