Objective: To develop a high-performance reconstruction framework that enables high-quality photoacoustic tomography (PAT) imaging under limited-view and sparse-view acquisition constraints. Impact Statement: The proposed method reduces the number of required acoustic transducers while maintaining image quality comparable to full-view systems, providing a practical and cost-efficient solution for biomedical PAT imaging. Introduction: PAT offers high-resolution visualization of biological tissues. However, restrictions such as reduced transducer counts or incomplete detection geometries render the inverse problem severely ill-posed, leading to marked degradation in reconstructed images. Although diffusion models have recently shown strong promise for image restoration, existing architectures can be computationally intensive or insufficiently expressive for the complexities of PAT.Methods: We introduce a time-driven transformer-based photoacoustic diffusion model (TT-PADM) that directly restores high-quality images from limited-view and sparse-view PAT reconstructions. TT-PADM uses a time-driven transformer within a time-dependent noise-estimation network, reducing model parameters by over 80% relative to conventional transformer designs while enhancing the generative capacity of the diffusion process. Results: Simulations and experimental results show that TT-PADM delivers high-fidelity reconstructions even under severely limited acquisition conditions, producing image quality comparable to full-view PAT systems. Quantitative and qualitative analyses show that TT-PADM consistently surpasses state-of-the-art reconstruction approaches, providing notable improvements in structural accuracy and noise suppression. Conclusion: TT-PADM offers a robust, parameter-efficient, and highly effective solution for PAT image restoration under practical hardware constraints, with strong potential for deployment in resource-limited biomedical imaging scenarios.

In hazy weather, suspended particles in the air cause significant image degradation by attenuating and scattering light. This degradation poses substantial challenges to subsequent image processing tasks, such as target recognition and positioning. Existing methods often struggle to balance global atmospheric light estimation with fine-detail preservation, leading to residual haze or over-enhancement and color distortion. Inspired by attention mechanisms, we design a hazy image restoration architecture utilizing an improved U-Net based generative adversarial network (GAN), enhanced by a novel hybrid attention mechanism. This mechanism integrates a global attention modulator, a window-based multi-head self-attention module, and a locally enhanced feedforward network, enabling the model to effectively capture both global and local image features while mitigating the artifacts seen in prior work. The network is trained using a tailored loss function that combines pixel loss, adversarial loss, and edge loss, specifically designed for the image dehazing task. Extensive experiments conducted on synthetic and real hazy images demonstrate that the proposed method consistently delivers high-quality dehazed images with exceptional clarity and contrast, outperforming several state-of-the-art methods.

Ring-Array photoacoustic tomography (PAT) systems have shown great promise in non-invasive biomedical imaging. However, images produced by these systems often suffer from quality degradation due to non-ideal imaging conditions, with common issues including blurring and streak artifacts. To address these challenges, we propose an image restoration method based on a conditional generative adversarial network (CGAN) framework. Our approach integrates a hybrid spatial and channel attention mechanism within a Residual Shifted Window Transformer Module (RSTM) to enhance the generator’s performance. Additionally, we have developed a comprehensive loss function to balance pixel-level accuracy, detail preservation, and perceptual quality. We further incorporate a gamma correction module to enhance the contrast of the network’s output. Experimental results on both simulated and in vivo data demonstrate that our method significantly improves resolution and restores overall image quality.

Transformer-based deep neural networks have demonstrated impressive performance in low-level visual tasks such as image deblurring. However, these networks often struggle with restoring spatially variant blurred images, resulting in outputs that lack detailed textures. This indicates that current transformer-based models fail to fully exploit their potential. To address this issue, we propose a mixed self-attention block by introducing a global attention modulator into the window-based self-attention mechanism. This approach leverages the complementary strengths of local and global feature extraction. We integrate this block into a U-shaped network, serving as the generator in a conditional generative adversarial network model. We further introduce a comprehensive loss function composed of adversarial loss, content loss, and edge loss for network training. Restoration quality is evaluated using both pixel-level and perceptual metrics to comprehensively assess visual fidelity. Moreover, the proposed model is specifically designed to handle spatially variant blur by combining localized window attention with global modulation across windows. This enables our model to adaptively focus on regions with varying blur severity and significantly improves restoration robustness under spatially variant conditions. Extensive experiments confirm the method's superior ability to restore spatially variant blurred images, achieving competitive performance on challenging real-world datasets.

In cases of insufficient lighting conditions, the obtained images of optical systems usually suffer from heavy noise, which subsequently has a negative impact on tasks like image segmentation, target detection, and edge extraction. Image denoising requires preserving the integrity of original information while eliminating irrelevant data from the signal. Regularization is an effective way to improve the performance of denoising algorithms, it achieves this by introducing additional constraints to ensure stable solutions. In this paper, we propose a hybrid regularization method which is based on the weighted combination of the L0-norm and L1-norm of image gradients. In order to obtain reliable denoising results, we have also developed a highly efficient alternately minimization algorithm to solve the resulting complex optimization problem. The algorithm utilizes variable splitting and Lagrange multipliers to determine the optimal solution, effectively transforming the initial problem into a simple convex optimization problem and a quadratic optimization problem, which can be rapidly solved in frequency domain. In the end, we conducted experiments to prove the efficiency of the proposed method. The results show that it is stable, efficient and the quality of the denoised images is comparable to some state-of-the-art methods.

In the fields of astronomical observation and fluorescence microscopic imaging, the obtained image is usually degraded by blur effects and Poisson noise. In this paper, we propose a robust hybrid regularization method consisting of total variation and L0-norm of image gradients and combine it with the Poisson distribution to formulate this kind of ill-posed problem. We also propose an efficient alternately minimization algorithm based on variable splitting and Lagrange multipliers to find the optimal solution, which can transform the original problem into a regularized deconvolution problem with quadratic fidelity term and a simple convex optimization problem. In the end, we carry out experiments to prove its convergence and effectiveness, the results show that the proposed method is stable, efficient and the quality of the restored image is comparable with some state-of-the-art methods.

The multi-band metamaterial absorbers studied today offer optimal sensing performance by maximizing the absorption at resonance frequencies. A constrained multi-objective optimization problem (CMOP) model is proposed to intelligently obtain the optimized geometrical parameters of the designed MA for optimal multi-band absorption. The proposed multi-band terahertz metamaterial absorber is formed by a patterned metallic patches (symmetric snowflake-shaped resonators) layer and a continuous metallic layer separated by a dielectric layer. The simulation results show that there are three discrete narrow resonance peaks with the absorption of 99.1%, 90.0%, and 99.9% in the range of 0.5–2 THz after being optimized by the proposed CMOP model. The reflection loss of all resonance modes is improved significantly compared with the conventional brute-force approach. Specifically, reflection loss at the highest resonance frequency is suppressed from -6.76 dB to -28.17 dB. Consequently, the reported MA design can be used as a refractive index sensor with the highest sensitivity of 495 GHz/RIU and the figure of merit (FoM) of 8.9 RIU −1 through a refractive index ranging from 1.0 to 1.6 at the analyte thickness of 18.5 μm. It is worth noting that most of the liquid samples have a refractive index ranging from 1.0 to 1.6. Therefore, the reported sensor can be used for liquid detection with high sensitivity.

ring-array photoacoustic tomography (PAT) system has been widely used in noninvasive biomedical imaging. However, the reconstructed image usually suffers from spatially rotational blur and streak artifacts due to the non-ideal imaging conditions. To improve the reconstructed image towards higher quality, we propose a concept of spatially rotational convolution to formulate the image blur process, then we build a regularized restoration problem model accordingly and design an alternating minimization algorithm which is called blind spatially rotational deconvolution to achieve the restored image. Besides, we also present an image preprocessing method based on the proposed algorithm to remove the streak artifacts. We take experiments on phantoms and in vivo biological tissues for evaluation, the results show that our approach can significantly enhance the resolution of the image obtained from ring-array PAT system and remove the streak artifacts effectively.

In the field of computer vision, edge line segment detection in images is widely used in tasks such as 3D reconstruction and simultaneous localization and mapping. Currently, there are many algorithms that primarily focus on detecting straight line segments in undistorted images, but they do not perform well in detecting edge line segments in distorted images. To address this quandary, the present study introduces a novel method of line segment identification founded on the principles of quadratic fitting. The method proposed utilizes the inherent property of a linear projection in a three-dimensional space, whereby it appears as a quadratic curve in a distorted two-dimensional image. This approach applies an iterative estimation process to ascertain the optimal parameters of the quadratic form that aligns with the edge contour. This process is facilitated by implementing an assumption and validation mechanism. Upon deriving the optimal model, it is then employed to identify the line segments that are encompassed within the edge contour. The experimental assessment of this novel method incorporates its application to both distorted and distortion-free image datasets. The method eliminates the necessity for preliminary processing to discarding distortions, thereby making it universally applicable to both distorted and non-distorted images. In addition to this, the experimental results based on the dataset indicate that the proposed algorithm in this paper achieves an average computational efficiency that is 27 times faster than traditional ones. Thus, this research will contribute to line segment detection in computer vision.

Photoacoustic tomography (PAT) system can reconstruct images of biological tissues with high resolution and contrast. However, in practice, the PAT images are usually degraded by spatially variant blur and streak artifacts due to the non-ideal imaging conditions and chosen reconstruction algorithms. Therefore, in this paper, we propose a two-phase restoration method to progressively improve the image quality. In the first phase, we design a precise device and measuring method to obtain spatially variant point spread function samples at preset positions of the PAT system in image domain, then we adopt principal component analysis and radial basis function interpolation to model the entire spatially variant point spread function. Afterwards, we propose a sparse logarithmic gradient regularized Richardson-Lucy (SLG-RL) algorithm to deblur the reconstructed PAT images. In the second phase, we present a novel method called deringing which is also based on SLG-RL to remove the streak artifacts. Finally, we evaluate our method with simulation, phantom and in vivo experiments, respectively. All the results show that our method can significantly improve the quality of PAT images.

The Perspective-n-Point problem is usually addressed by means of a projective imaging model of 3D points, but the spatial distribution and quantity of 3D reference points vary, making it difficult for the Perspective-n-Point algorithm to balance accuracy, robustness, and computational efficiency. To address this issue, this paper introduces Hidden PnP, a hidden variable method. Following the parameterization of the rotation matrix by CGR parameters, the method, unlike the existing best matrix synthesis technique (Gröbner technology), does not require construction of a larger matrix elimination template in the polynomial solution phase. Therefore, it is able to solve CGR parameter rapidly, and achieve an accurate location of the solution using the Gauss–Newton method. According to the synthetic data test, the PnP algorithm solution, based on hidden variables, outperforms the existing best Perspective-n-Point method in accuracy and robustness, under cases of Ordinary 3D, Planar Case, and Quasi-Singular. Furthermore, its computational efficiency can be up to seven times that of existing excellent algorithms when the spatially redundant reference points are increased to 500. In physical experiments on pose reprojection from monocular cameras, this algorithm even showed higher accuracy than the best existing algorithm.

In photoacoustic tomography (PAT), image reconstruction refers to the formation process from photoacoustic signals to target images, which has an important influence on the image quality. At present, most reconstruction algorithms assume that the medium is homogeneous, which may cause distortion and artifacts in the reconstructed images. Therefore, considering the heterogeneity of the medium is important for accurate image reconstruction in PAT. The iterative reconstruction (IR) algorithm can incorporate the information of imaging system and media, and thus can provide high-quality image reconstruction. In this work, we investigate the IR algorithm in PAT with heterogeneous media based on point source response. We obtain the system matrix by calculating the photoacoustic signal of each point source in heterogeneous media based on the k-space pseudospectral method. The target image is reconstructed iteratively with the media information-coupled system matrix and the total variation (TV) regularization. We take a set of simulations to verify the effectiveness of the IR algorithm in heterogeneous media. The results demonstrate the validity and rationality of the proposed method. The work provides a new method for accurate reconstruction of photoacoustic images.

We propose to combine a variety of regularization terms and design a non-blind image deconvolution algorithmic framework which is based on the split-Bregman approach. With the proposed algorithm, the original problem can be decomposed into simple sub-problems and solved efficiently by variable splitting and penalty technology. Furthermore, we also propose an acceleration scheme for restoring large scale blurred image which is based on image segmentation and parallel computing of GPU and multi-core CPU. Experimental results show that our approach can achieve restored image of high quality which is comparable with some state of the art methods, and the efficiency of the algorithm can be significantly enhanced with the proposed acceleration scheme for restoring large scale blurred image.

We propose a dehazing problem model with hybrid regularization and design an effective algorithm to restore the latent image and transmission map simultaneously. In the proposed dehazing problem model, we use the total variation (TV) to regularize the latent image and adopt the hybrid TVand L-0-norm (TV-L-0) regularization to model the transmission map. In the proposed optimization algorithm, we first use the dark channel prior to achieve an initial guess of the global atmospheric light and transmission map. Then we convert the original problem into two subproblems: one aims to update the latent image based on TV regularization, whereas the other estimates the transmission map with hybrid TV-L-0 regularization. Both of the subproblems can be solved efficiently with variable splitting and penalty technology, and the minimizer is reached by alternately solving the two subproblems. Experimental results show that our approach can achieve a high-quality restored image that is comparable to some state-of-the-art methods. (c) 2022 SPIE and IS&T

Abstract. We propose a dehazing problem model with hybrid regularization and design an effective algorithm to restore the latent image and transmission map simultaneously. In the proposed dehazing problem model, we use the total variation (TV) to regularize the latent image and adopt the hybrid TV and L0-norm (TV–L0) regularization to model the transmission map. In the proposed optimization algorithm, we first use the dark channel prior to achieve an initial guess of the global atmospheric light and transmission map. Then we convert the original problem into two subproblems: one aims to update the latent image based on TV regularization, whereas the other estimates the transmission map with hybrid TV–L0 regularization. Both of the subproblems can be solved efficiently with variable splitting and penalty technology, and the minimizer is reached by alternately solving the two subproblems. Experimental results show that our approach can achieve a high-quality restored image that is comparable to some state-of-the-art methods.

This paper presents a novel reconfigurable crawling robot based on an origami twisted tower structure. Compared with other origami structures, the twisted tower can achieve extension, contraction, and bending motions as the flexible body parts in robotic designs. The kinematics of a one-layer twisted tower were analyzed with rotation and bending angles. The mechanical properties of the one-layer, two-layer, and four-layer twisted towers were compared with compression experiments. A rope-motor-driven crawling robot was designed to realize forward, backward, left-turning, and right-turning motions. Two types of crawling robot with specific sliding feet were developed to adapt to different ground conditions: one made of rubber, and the other embedded with an electromagnet. The experimental results show that the proposed robots can move at an average forward speed of 0.48 cm/s on a wooden desk, and at 0.52 cm/s forward speed or 0.65 cm/s backward speed on an iron platform.

In photoacoustic tomography, an ultrasonic transducer array is usually used to receive photoacoustic signals, which is expensive to manufacture, and the number of array elements has an important impact on the final imaging quality. To improve photoacoustic image quality reconstructed under sparse view conditoin, this study proposes a modified U-Net based on the replacement of the skip connection in a conventional U-Net with continuous convolutional layers, thereby increasing the matching degree of features transferred from the encoder to the decoder. Furthermore, the loss function based on the structural similarity index measure is used to train the network. Experimental results based on simulation and in vivo dataset show that compared with the conventional U-Net, the modified U-Net achieves more image details and the quality of the reconstructed image is significantly better.

The detection of rail top crack is of great significance in ensuring the safe operation of railway. Based on the principle of magnetic flux leakage detection and Faraday magneto-optical effect, a high-resolution and non-destructive magneto-optical imaging detection method is proposed in this paper. This paper analyses the principle of magneto-optical imaging, establishes a rail magnetic flux leakage detection experimental system based on magneto-optical effect, and detects the rail specimen with crack through experiment. The experimental results show that the change of crack width and depth will affect the magneto-optical imaging results, and the minimum crack size that can be detected by this experimental system is 0.4mm wide and 0.5mm deep. This paper realizes the detection of rail crack defects by using magneto-optical imaging method, and provides the basis for building an efficient, portable and high-resolution rail non-destructive testing equipment.