Chaotic systems play a key role in modern image encryption due to their sensitivity to initial conditions, ergodicity, and complex dynamics. However, many existing chaos-based encryption methods suffer from vulnerabilities, such as inade-quate permutation and diffusion, and suboptimal pseudorandom properties. To address these issues, this paper presents the Knot-like Unique Novel-Scan Image Encryption (Kun-IE). The framework comprises two main components: The 2D Sin–Cos Pi Hyperchaotic Map (2D-SCPHM), which provides a broader chaotic range and superior pseudorandom sequence generation, and the Knot-like Unique Novel-Scan Algorithm (Kun-SCAN), a novel permutation mechanism that markedly reduces pixel correlations and enhances resistance to statistical attacks. Kun-IE is flexible and supports encryption for images of any size. Experimental results and security analyses demonstrate its robustness against various cryptanalytic attacks, making it a strong solution for secure image communication. The code is available at this link.

The rise of digital medical imaging, like MRI and CT, demands strong encryption to protect patient data in telemedicine and cloud storage. Chaotic systems are popular for image encryption due to their sensitivity and unique characteristics, but existing methods often lack sufficient security. This paper presents the Three-dimensional Diffusion Algorithm and Deep Learning Image Encryption system (TDADL-IE), built on three key elements. First, we propose an enhanced chaotic generator using an LSTM network with a 1D-Sine Quadratic Chaotic Map (1D-SQCM) for better pseudorandom sequence generation. Next, a new three-dimensional diffusion algorithm (TDA) is applied to encrypt permuted images. TDADL-IE is versatile for images of any size. Experiments confirm its effectiveness against various security threats. The code is available at https://github.com/QuincyQAQ/TDADL-IE.

Underwater Image Restoration (UIR) remains a challenging task in computer vision due to the complex degradation of images in underwater environments. While recent approaches have leveraged various deep learning techniques, including Transformers and complex, parameter-heavy models to achieve significant improvements in restoration effects, we demonstrate that pure CNN architectures with lightweight parameters can achieve comparable results. In this paper, we introduce UIR-PolyKernel, a novel method for underwater image restoration that leverages Polymorphic Large Kernel CNNs. Our approach uniquely combines large kernel convolutions of diverse sizes and shapes to effectively capture long-range dependencies within underwater imagery. Additionally, we introduce a Hybrid Domain Attention module that integrates frequency and spatial domain attention mechanisms to enhance feature importance. By leveraging the frequency domain, we can capture hidden features that may not be perceptible to humans but are crucial for identifying patterns in both underwater and on-air images. This approach enhances the generalization and robustness of our UIR model. Extensive experiments on benchmark datasets demonstrate that UIR-PolyKernel achieves state-of-the-art performance in underwater image restoration tasks, both quantitatively and qualitatively. Our results show that well-designed pure CNN architectures can effectively compete with more complex models, offering a balance between performance and computational efficiency. This work provides new insights into the potential of CNN-based approaches for challenging image restoration tasks in underwater environments. The code is available at https://github.com/CXH-Research/UIR-PolyKernel.

Lensless imaging stands out as a promising alternative to conventional lens-based systems, particularly in scenarios demanding ultracompact form factors and cost-effective architectures. However, such systems are fundamentally governed by the Point Spread Function (PSF), which dictates how a point source contributes to the final captured signal. Traditional lensless techniques often require explicit calibrations and extensive pre-processing, relying on static or approximate PSF models. These rigid strategies can result in limited adaptability to real-world challenges, including noise, system imperfections, and dynamic scene variations, thus impeding high-fidelity reconstruction. In this paper, we propose LensNet, an end-to-end deep learning framework that integrates spatial-domain and frequency-domain representations in a unified pipeline. Central to our approach is a learnable Coded Mask Simulator (CMS) that enables dynamic, data-driven estimation of the PSF during training, effectively mitigating the shortcomings of fixed or sparsely calibrated kernels. By embedding a Wiener filtering component, LensNet refines global structure and restores fine-scale details, thus alleviating the dependency on multiple handcrafted pre-processing steps. Extensive experiments demonstrate LensNet's robust performance and superior reconstruction quality compared to state-of-the-art methods, particularly in preserving high-frequency details and attenuating noise. The proposed framework establishes a novel convergence between physics-based modeling and data-driven learning, paving the way for more accurate, flexible, and practical lensless imaging solutions for applications ranging from miniature sensors to medical diagnostics. The link of code is https://github.com/baijiesong/Lensnet.

Accurate segmentation and tracking of cells are crucial in biomedical research. The latest methods utilize multilayer convolution or block based region similarity measurement to process foreground background relationships, but under low signal-to-noise ratio conditions, there is insufficient target pattern recognition and boundary detail characterization, which can easily lead to segmentation errors and boundary blurring. To address this issue, we propose SimCNet, a segmentation network based on similarity measurement and texture enhancement. The network consists of three modules: the Global Pattern Sorting and Focusing Module (GPRF), which uses pixel level feature histogram aggregation and a Fourier based feedforward network to create similarity fingerprints for different target patterns, enhancing the recognition ability of different regions. The Multi Scale Feature Collaborative Capture Module (MFCM) enhances the global and inter channel information exchange of GPRF through the fusion of multi-scale fusion mechanisms, eliminating semantic gaps. Texture Feature Enhancement Module (TFEM), which uses quaternion convolution to enrich texture representations in similarity feature maps and enhance boundary perception. Experiments have shown that SimCNet exhibits excellent performance and generalization on multiple publicly available datasets such as MoNuSeg.

Domain adaptation (DA) is designed to tackle the problem of label scarcity in the target domain by transferring knowledge to it. However, there are two critical challenges in DA : 1) insufficient discriminative power of learned features, and 2) inadequate exploration of inter-sample relationships. This study proposes a novel framework, Joint Consistency-Driven Dual-Domain Discriminative Learning (JCD3L) to overcome these limitations. This framework encompasses two components: Inter-domain Collaborative Feature Enhancement (ID-CFE) and Joint Semantic-Spatial Consistency Constraint (JSSCC). Firstly, ID-CFE applies angular margin (AM) loss to the source domain while imposing entropy regularization on the target domain, establishing a dual-domain discriminative enhancement mechanism for feature representations. Additionally, a novel consistency regularization, JSSCC, is proposed to thoroughly explore the interrelationships among samples. This regularization leverages the label-semantics and feature-semantics to refine the alignment process. To verify the effectiveness of our work, comprehensive experiments are conducted across three widely used benchmarks and the results demonstrate considerable improvements.

Gesture recognition using millimeter wave (mmWave) radar has gained increasing attention in human-computer interaction and automation systems. It is known that the point cloud data-based and spectrum data-based methods are typically two types of gesture recognition methods. Since the spectrum data-based methods are usually difficult to collect due to the high spectrum, the point cloud data consisting of sequential information frames is considered. However, the inherent variability in gesture dynamics, coupled with the latency and uncertainty in radar data acquisition, results in inconsistent frame lengths in point cloud data, posing a significant challenge for accurate gesture recognition. To this end, a spatial-temporal gesture network (STGNet) is proposed, where a hybrid convolutional neural networks (CNNs) and long short-term memory (LSTM) framework is adopted to capture spatial and temporal information of point cloud data. Specifically, the CNN module focuses on robust spatial feature extraction, while the LSTM module models temporal sequences, accommodating variable frame lengths and complex gesture dynamics. To further mitigate the overfitting problem, especially under imbalanced or limited sample conditions, the synthetic minority over-sampling technique (SMOTE) is employed to balance class distributions and enhance generalization. Finally, the effectiveness of the proposed STGNet is evaluated on a publicly available dataset, demonstrating its satisfactory performance.

Low-light image enhancement (LLE) aims to improve the visual quality of images captured in poorly lit conditions, which often suffer from low brightness, low contrast, noise, and color distortions. These issues hinder the performance of computer vision tasks such as object detection, facial recognition, and autonomous driving. Traditional enhancement techniques, such as multi-scale fusion and histogram equalization, fail to preserve fine details and often struggle with maintaining the natural appearance of enhanced images under complex lighting conditions. Although the Retinex theory provides a foundation for image decomposition, it often amplifies noise, leading to suboptimal image quality. In this paper, we propose the Dual Light Enhance Network (DLEN), a novel architecture that incorporates two distinct attention mechanisms, considering both spatial and frequency domains. Our model introduces a learnable wavelet transform module in the illumination estimation phase, preserving high- and low-frequency components to enhance edge and texture details. Additionally, we design a dual-branch structure that leverages the power of the Transformer architecture to enhance both the illumination and structural components of the image. Through extensive experiments, our model outperforms state-of-the-art methods on standard benchmarks. The code is available at: https://github.com/LaLaLoXX/DLEN

Enhancing underwater images is crucial for exploration. These images face Enhancing underwater images is crucial for exploration. These images face visibility and color issues due to light changes, water turbidity, and bubbles. Traditional prior-based methods and pixel-based methods often fail, while deep learning lacks sufficient high-quality datasets. We introduce the Multi-Axis Conditional Lookup (MAC-Lookup) model, which enhances visual quality by improving color accuracy, sharpness, and contrast. It includes Conditional 3D Lookup Table Color Correction (CLTCC) for preliminary color and quality correction and Multi-Axis Adaptive Enhancement (MAAE) for detail refinement. This model prevents over-enhancement and saturation while handling underwater challenges. Extensive experiments show that MAC-Lookup excels in enhancing underwater images by restoring details and colors better than existing methods. The code is https://github.com/onlycatdoraemon/MAC-Lookup.

Document images are often degraded by various stains, significantly impacting their readability and hindering downstream applications such as document digitization and analysis. The absence of a comprehensive stained document dataset has limited the effectiveness of existing document enhancement methods in removing stains while preserving fine-grained details. To address this challenge, we construct StainDoc, the first large-scale, high-resolution (2145 x 2245) dataset specifically designed for document stain removal. StainDoc comprises over 5,000 pairs of stained and clean document images across multiple scenes. This dataset encompasses a diverse range of stain types, severities, and document backgrounds, facilitating robust training and evaluation of document stain removal algorithms. Furthermore, we propose StainRestorer, a Transformer-based document stain removal approach. StainRestorer employs a memory-augmented Transformer architecture that captures hierarchical stain representations at part, instance, and semantic levels via the DocMemory module. The Stain Removal Transformer (SRTransformer) leverages these feature representations through a dual attention mechanism: an enhanced spatial attention with an expanded receptive field, and a channel attention captures channel-wise feature importance. This combination enables precise stain removal while preserving document content integrity. Extensive experiments demonstrate StainRestorer's superior performance over state-of-the-art methods on the Stain-Doc dataset and its variants StainDoc.Mark and Stain-Doc.Seal, establishing a new benchmark for document stain removal. Our work highlights the potential of memory-augmented Transformers for this task and contributes a valuable dataset to advance future research.

Underwater image enhancement (UIE) plays a crucial role in various marine applications, but it remains challenging due to the complex underwater environment. Current learning-based approaches frequently lack explicit incorporation of prior knowledge about the physical processes involved in underwater image formation, resulting in limited optimization despite their impressive enhancement results. This paper proposes a novel deep unfolding network (DUN) for UIE that integrates color priors and inter-stage feature transformation to improve enhancement performance. The proposed DUN model combines the iterative optimization and reliability of model-based methods with the flexibility and representational power of deep learning, offering a more explainable and stable solution compared to existing learning-based UIE approaches. The proposed model consists of three key components: a Color Prior Guidance Block (CPGB) that establishes a mapping between color channels of degraded and original images, a Nonlinear Activation Gradient Descent Module (NAGDM) that simulates the underwater image degradation process, and an Inter Stage Feature Transformer (ISF-Former) that facilitates feature exchange between different network stages. By explicitly incorporating color priors and modeling the physical characteristics of underwater image for-mation, the proposed DUN model achieves more accurate and reliable enhancement results. Extensive experiments on multiple underwater image datasets demonstrate the superiority of the proposed model over state-of-the-art methods in both quantitative and qualitative evaluations. The proposed DUN-based approach offers a promising solution for UIE, enabling more accurate and reliable scientific analysis in marine research. The code is available at https://github.com/CXH-Research/UIE-UnFold.