Cheng Wu

With the advancement of transportation and economic development, rail transportation has become a critical mode of transit, and rail health monitoring is essential for ensuring its operational safety. However, traditional signal processing methods often fail in complex vibration and noise environments due to spectrum overlap and non-stationary characteristics. In this context, we propose a novel dual-branch deep network architecture, Time-Domain Acoustic Signal Separation Network (TDASS), which integrates a time-frequency-aware attention mechanism driven by local gradients to effectively distinguish between low-frequency periodic noise and high-frequency impulsive defect events for blind source separation of rail defect signals. The process by which neural networks learn to "listen" and "separate" is pivotal for both model optimization and the interpretability of the learning process. To further enhance the network's discriminative ability and improve the transparency of feature extraction, a triplet loss strategy was introduced, enforcing discriminative representation learning by modelling the anchor-positive-negative relationship between predicted and ground-truth signals. Extensive experiments on real-world acoustic emission (AE) datasets demonstrate that our method achieves superior performance in terms of scale-invariant signal-to-noise ratio (SI-SNR) and waveform similarity coefficients, with an average similarity of 0.9719 and an average SI-SNR of 20.18 dB in the rail defect separation task. These results validate the efficacy of combining gradient-aware frequency attention with structural task constraints for robust and accurate defect signal extraction.

Light field rendering is widely applied to virtual reality (VR), augmented reality (AR), mixed reality (MR) and extended reality (XR). For photorealistic light field displays, it requires a dense view sampling of the scene. However, in dynamic immersive interactions, the available observations are often too sparse to synthesize the complete light field required for a high-fidelity display. Therefore, it poses a huge challenge for generating photometrically consistent views between the virtual and real world. Here, we introduce a neural illumination estimation and editing framework for adaptive light field synthesis. The proposed method can explicitly encode intrinsic parameters of illumination from one single sampling view, which is used for a hybrid-guided generative network to synthesize photometrically plausible dense views of the scene under the guidance of a complete rendering model. It deconstructs the baked-in lighting to enable consistent and high-fidelity relighting from any viewpoint. Our method estimates and edits illumination with only 0.2397 W m ⁻² irradiance error and 7.02 ^∘ angular deviation, yielding synthesized images with an average 17.0% improvement in PSNR and a 51.2% reduction in LPIPS. This work presents a practical pathway towards truly interactive and adaptive digital light fields, enabling photorealistic content generation for the next generation of near-eye displays and computational imaging systems.

Deep learning has achieved significant success in stereo matching, with its training process often supervised by LiDAR measurements. However, the sparsity of real-world LiDAR data limits the ability of deep models to extract effective features from stereo images. To address this issue, a novel deep learning-based framework called sparse LiDAR point cloud supervised stereo matching (SLSM-Net) is proposed. Specifically, dense reconstruction of sparse single-frame point clouds is first designed to avoid the error introduction with the mergence of multi-frame point clouds. To effectively densify point clouds of objects in local areas, stereo images are utilized as supervision information to train the deep models. Furthermore, a coarse-to-fine structure of the deep model is designed for stereo matching. A self-supervised learning strategy, which employs a photometric consistency constraint, is second proposed along with fully supervised learning to obtain dense and precise supervision information. This stage generates coarse disparity maps from stereo images. Finally, to fully leverage the complementary characteristics of LiDAR and stereo cameras, multi-scale feature fusion of point clouds and stereo images is performed by a residual block, where the feature maps of point clouds are derived from the densification reconstruction. This stage refines the results. Experimental results indicate that SLSM-Net outperforms current state-of-the-art methods, demonstrating superior performance in stereo matching.

Diagnostic imaging in sports medicine includes traditional imaging modalities such as x‐ray, computed tomography (CT), and magnetic resonance imaging (MRI). Despite having certain advantages, these imaging techniques often have lower sensitivity and specificity, making it difficult to detect soft tissue injuries and early‐stage cartilage damage. They also lack the ability to assess the biomechanical properties and functional states of tissues. Photoacoustic imaging (PAI) offers a powerful, non‐ionizing, and cost‐effective alternative to traditional imaging techniques in the diagnosis and therapeutic monitoring of sports injuries. PAI combines the benefits of optical imaging and ultrasound to provide high‐resolution images of deep tissues, including tendons and ligaments. This technology uses pulsed lasers to irradiate tissues, causing thermal expansion and generating ultrasound waves, which are then captured and converted into images. PAI is particularly adept at depicting blood vessels and soft tissues with high resolution and sensitivity to the optical absorption contrasts of oxy‐ and deoxyhemoglobin. It can assess tissue oxygenation and metabolic activities, which are crucial for evaluating the healing process in sports injuries. Herein, the role of PAI in sports medicine is assessed and particularly its advantages over traditional imaging methods such as x‐rays, CT scans, and MRI scans in diagnosing musculoskeletal injuries.

Optical information synthesis, which fuses LiDAR and optical cameras, has the potential for highly detailed 3D representations. However, due to the disparity of information density between point clouds and images, conventional matching methods based on points often lose significant information. To address this issue, we propose a regional matching method to bridge the differences in information density between point clouds and images. In detail, fine semantic regions are extracted from images by analyzing their gradients. Simultaneously, point clouds are transformed into meshes, where each facet corresponds to a coarse semantic region. Extrinsic matrices are used to unify the point cloud coordinate system with the image coordinate system. The mesh is further subdivided based on the guidance of image texture information to create regional matching units. Within each matching unit, the information density of the point cloud and the image is carefully balanced at a semantic level. The texture features of the image are well preserved in the transformed mesh structure. Consequently, the proposed texture synthesis method significantly enhances the overall quality and realism of the 3D imaging.

Iris recognition is widely regarded as one of the most reliable biometric identification technologies. Traditional methods, such as the Daugman algorithm typically normalize the annular iris region into a rectangular format during the preprocessing stage, followed by feature extraction and matching. However, these preprocessing steps often introduce distortions and struggle to adapt to multiresolution images, leading to inaccurate feature encoding. In response to these limitations, we propose a weak preprocessing algorithm for iris recognition that effectively preserves both grayscale and structural information of the iris. This approach is highly adaptable to varying image resolutions by leveraging a multiscale structural information extraction framework. It demonstrates significant improvements, achieving a matching accuracy of 96.67% on our proprietary dataset and 90% on the CASIA‐IrisV4 dataset. Compared to the Daugman and OsIris 4.0 algorithm using weak preprocessing schemes, our approach improves accuracy by 15.55% and reduces matching time by 16%. More importantly, this method presents a new idea that is different from traditional preprocessing methods with wider adaptability. It offers considerable potential for real‐world applications in security, with promising prospects for further integration with deep learning techniques.

Point cloud densification is an effective measure to alleviate the sparseness of point clouds. In 3D vision, the positional relationship of multi-frame point clouds is applied to point cloud densification research to explain the rationality of the source of supplementary points. Among them, scene flow estimation is effective for dynamic scenes. However, scene flow estimation of long-sequence dynamic point clouds is prone to cumulative positioning errors. In order to solve this problem, this paper proposes to correct the scene flow estimation results from a timing perspective based on Kalman filtering. Specifically, the scene flow estimation model is first optimized according to the pyramid structure to improve the reliability of point cloud feature extraction. Then, combined with the temporal relationship of the point clouds in the previous and later frames, the point cloud is reconstructed uniformly to complete the densification of the point cloud. Finally, the densified point cloud is applied to the 3D detection task. Results on the KITTI3D tracking dataset show that the point cloud densification method based on scene flow estimation can effectively improve the performance of LiDAR-only detectors.

The spectral super-resolution (SpeSR) from multispectral images (MSIs) to hyperspectral images (HSIs) can bring rich spectral information. The deep learning-based methods have demonstrated their powerful ability for the SpeSR task, which requires the paired HSI/MSI to train the model. However, HSIs and MSIs are always obtained at different times and under different imaging conditions, covering different areas. To address this issue, in this article, a framework named BliEstGAN based on the generative adversarial network (GAN) is proposed to estimate the spectral resolution degradation between unpaired HSIs and MSIs that can be used for the blind SpeSR. Specifically, each MSI imaging sensor has its own unique spectral sampling process, which can be modeled as a spectral degradation from its paired HSI. Different spectral degradations can be discriminated by the deep model. Therefore, the generator of the GAN is used to estimate the spectral degradation from HSIs to MSIs, and the discriminator of the GAN is adopted to distinguish whether the estimated and real spectral degradation is similar. The MSIs and HSIs are easy to discriminate against by the discriminator because their spatial resolutions are different. Furthermore, according to the imaging sensor mechanism, some special regularization terms are designed for the generator to guarantee its correct convergence. Finally, the estimated spectral resolution degradation can be adopted to generate HSI/MSI pairs for the supervised learning-based SpeSR methods. Experimental results demonstrate the effectiveness of the proposed method.

It is necessary to explore an effective point cloud completion mechanism that is of great significance for real-world tasks such as autonomous driving, robotics applications, and multi-target tracking. In this paper, we propose a point cloud completion method using a self-supervised transformer model based on the contextual constraints of scene flow. Our method uses the multi-frame point cloud context relationship as a guide to generate a series of token proposals, this priori condition ensures the stability of the point cloud completion. The experimental results show that the method proposed in this paper achieves high accuracy and good stability.