Zhuoyi Yang

Spectral super-resolution (SSR) from RGB response can achieve flexible applications and high resolution (both spatial and spectral) under low-cost conditions, which is beneficial in various tasks like surface coating, target recognition, and vegetation monitoring. However, most existing SSR works are based on the overall features of the image to pursue lower average errors, while such averaging effect could weaken the improvement of higher reconstruction accuracy for individual pixels, and also leads to deeper and more complex models. To address these problems, we propose a two-stage method focused on the local phase and color similarity from a pixel perspective. In the first stage, a selection strategy named Tristimulus Color Congruency (TCC) is introduced to extract the color similarity of optical images and guide the selection of pixels to enrich the training process, which is very sparse compared to the whole image (less than 1%). In the second stage, the Spectral Extension Network (SEN) with several easy-to-deploy blocks is constructed to complete an effective and efficient single-pixel spectrum prediction. Single pixel computation time of our model is compressed to the order of μ s, and the method is evaluated in three public benchmarks (Munsell-1269, CAVE-real, and AeroRIT). In the hyperspectral image reconstruction task, our method improves the reconstruction performance by over 40% overall test compared to the baseline and shows consistency in different environments. Besides, as pixel-based, our method can also serve as a plug-and-play model to improve the performance on any region of any size or discrete pixels of interest. The reference code is available at https://github.com/Eahein-H/TCC-SEN .

High-Resolution Range Profile (HRRP)-based space object classification is severely limited by aspect sensitivity. Inspired by the intrinsic complementarity between HRRP and LiDAR point clouds, this work investigates the feasibility and effectiveness of fusing these two modalities to address this limitation. We propose the Point-HRRP-Net framework. This framework employs dual-stream extractors to independently encode HRRP electromagnetic signatures and 3D point cloud geometric topologies. Subsequently, a Bi-Directional Cross-Attention (Bi-CA) mechanism is designed to fuse the two modalities. To enable information interaction, this mechanism utilizes point-to-point attention to correlate radar scattering features with 3D geometric points, thereby constructing a comprehensive target representation. Due to data scarcity, we constructed a paired simulation dataset for evaluation. Experimental results demonstrate that the proposed framework consistently outperforms its constituent single-modality baselines. The model achieves 57.67% accuracy on the 180° split and demonstrates generalization capability to unseen viewpoints. Ablation studies further validate the efficacy of the Bi-CA mechanism and the selected feature extractors. Finally, we assess the potential sim-to-real discrepancies and evaluate deployment feasibility across various hardware platforms.

Spatial Phase Prediction from intensity image without auxiliary sensors is a challenging task due to the compressed phase information and the increase in complexity with varying optical systems. Many advanced works focus primarily on the adaptability to extended light sources, while having yet to construct a feature map that is robust and sufficient enough to represent the characteristics of the aberration, leading to some problems, such as a minimum light intensity limit, a small input size, and failing to remain optimal with different phase ranges. To tackle these problems, we apply both the Fourier transform and the multi-scale wavelet transform in the feature mapping process, constructing a high-frequency concentrated aberration feature sequence (AFS). To better adapt to the learning complexity, we formulate an effective and lightweight model, named aberration sensing convolutional neural network (ASCNN), under the supervised framework that allows efficient online computation. The results demonstrate that compared to the baseline feature, the performance of the proposed AFS improves by around 30%. Besides, the model ASCNN achieves high performance in aberration retrieval, with an average RMSE better than 0.0143 λ under the initial condition of ±0.25 λ , and the SSIM exceeding 96% between the reconstructed and ground-truth phases. Furthermore, the proposed method is evaluated on both scalar diffraction and the polarized SLM system to demonstrate the robustness and the broad potential for applications.

Robust radar object classification is a challenging task, primarily due to the aspect sensitivity limitation of one-dimensional High-Resolution Range Profile (HRRP) data. To address this, we propose Point-HRRP-Net. This multi-modal framework integrates HRRP with 3D LiDAR point clouds via a Bi-Directional Cross-Attention (Bi-CA) mechanism to enable deep feature interaction. Since paired real-world data is scarce, we constructed a high-fidelity simulation dataset to validate our approach. Experiments conducted under strict angular separation demonstrated that Point-HRRP-Net consistently outperformed single-modality baselines. Our results also verified the effectiveness of Dynamic Graph CNN (DGCNN) for feature extraction and highlighted the high inference speed and the potential of Mamba- based architectures for future efficient designs. Finally, this work validates the feasibility of the proposed approach in simulated environments, establishing a foundation for robust object classification in real-world scenarios.

This paper presents a novel free-space optical Angle-of-Arrival (AOA) estimation method based on arrayed waveguide coherent mode decoding, aiming to surpass the inherent limitations of traditional AOA detection technologies, which face significant challenges in achieving miniaturization, low complexity, and high reliability. The method utilizes the AOA-related phase differences generated by the propagation and interference of incident light in an arrayed input waveguide, forming multi-beam interference fringes at the output end of the slab waveguide. This pattern is then sampled by an arrayed output waveguide to produce an intensity sequence, which is then fed into a trained CNN–Attention Regressor for AOA estimation. This study innovatively applies the method to decoding the spatial angular information of optical signals. Simulation results demonstrate the exceptional performance of our approach, achieving a Mean Absolute Error (MAE) of 0.0142° and a Root Mean Square Error (RMSE) of 0.0193° over a 40° field of view. This precision is significantly superior to conventional peak–linear calibration methods and other common neural network architectures, and exhibits remarkable robustness against simulated phase noise and manufacturing tolerances. This research demonstrates the powerful synergy between integrated photonics and deep learning, paving the way for a new class of highly integrated, robust, and high-performance on-chip optical sensors.

A novel approach for laser coherent beam combination (CBC) utilizing the self-imaging effect in plasma waveguides is presented in this study, which enables the transmission of ultrashort laser pulses at intensities above the bulk damage threshold of conventional solid optical waveguides. The feasibility of self-imaging-based CBC in plasma waveguides was simulated and verified, demonstrating favorable combining efficiency and beam quality. This work explores the adaptive tuning of waveguide length via dynamic adjustment of plasma density, addressing the critical issue of fabrication tolerances in traditional waveguide systems. With CBC via plasma waveguide, this study offers support for the development of robust, high-power laser systems with enhanced beam quality and operational stability.