Accurate image reconstruction from low-sampling measurements remains a crucial challenge in image compressed sensing (CS). Image CS has attracted increasing research interest, with deep learning approaches being extensively studied. Deep learning based methods reduce computational complexity at the inference stage compared with traditional iterative solvers and can improve reconstruction quality. In particular, methods built on transformer architectures have achieved remarkable success in tasks involving image reconstruction and restoration. However, as the depth of the model increases, some content information may be attenuated during feature propagation. To alleviate the issue, this paper proposes a content-aware transformer network (CATNet) for image compressed sensing. It focuses on content feed-forward and channel self-attention to effectively obtain sufficient feature representation. In the initial reconstruction stage, this paper employs trainable sensing matrix to adaptively capture sparse structures from the image, which helps improve measurement efficiency. In the deep reconstruction stage, this paper introduces the content-focused feed-forward network (CFFN) to strengthen the effective content features. Besides, this paper employs the channel-focused self-attention (CFSA) to enhance global features and integrate convolution to refine local details. Finally, this paper adopts a multi-stage supervision to ensure sufficient training. Comprehensive experiments conducted on 5 widely used datasets demonstrate the strong performance and superiority of CATNet over 9 representative methods, especially under extremely low sampling rates. At CS ratio of 0.05, CATNet achieves competitive results, with PSNR/SSIM values of 22.25/0.6907 on Set5, 21.91/0.6623 on Set11, 21.99/0.6664 on Set14, 23.97/0.6964 on BSD68, and 20.61/0.5585 on Urban100. Moreover, the method has been successfully implemented in the self-developed single-pixel imaging optical system, further demonstrating its applicability.

Salient object detection in remote sensing images (RSI-SOD) plays a vital role in enabling large-scale environmental perception for embodied intelligence systems. Despite growing interest, existing methods often underperform in complex urban settings characterized by cluttered backgrounds and significant scale variations, suffering from either blurred object boundaries or high computational costs. To address these issues, we propose a perceptual gating mamba network (PGMNet) that accurately and efficiently detects objects with a global receptive field. The network first employs a spatial neighboring scanning strategy to extract structurally coherent image patches. A gated focus-aware mamba fusion module is then designed to enhance spatial coherence across these patches through joint channel focusing, spatial attention, and a gating mechanism, thereby improving localization accuracy. Furthermore, a structure-preserving upsampling aggregation module is developed to reconstruct complete object contours by aligning and aggregating multi-level features during decoding. Extensive experiments on two benchmark datasets demonstrate that PGMNet outperforms 12 competing methods, validating its effectiveness and robustness in complex urban environments.

Machine vision plays a crucial role in Earth observation. As a fundamental and challenging task in vision systems, image registration faces new challenges due to increasing collaborative and customization applications. The prevalence of more false matches and low-precision matches is particularly evident in complex and changeable scenarios. In this article, we propose a robust image registration method via topology sort and vision consistence. Initial candidate matches are established via the nearest neighbor ratio of image intensity descriptors. A topological sort across the proximity structure around the point pairs is defined to assess the reliability of candidate matched pairs, effectively eliminating more false matches while retaining highly reliable point pairs. To preserve more point pairs, we develop a spatial visual inspection mechanism to further determine the potential matches from the remaining pairs that do not satisfy the previous topological constraint. During vision inspection, the spatial transformation model is simultaneously estimated. Experimental results on public datasets show that the proposed method outperforms state-of-the-art approaches in both matching accuracy and visual effect.

Underwater images suffer from different types of degradation such as blur and color cast. It is difficult to obtain images with both color equalization and rich texture in various underwater scenes. To alleviate these issues, this paper proposes a reflected light-aware multi-scale progressive restoration network. A restoration framework is designed based on physical imaging model. It can accurately remove scattering blur of various underwater images and output a preliminary restoration result. A multi-scale progressive enhancement module is proposed to further enrich the image details and improve the generalization ability of the model by fully extracting detailed and spatial features. For the issues of color cast and low contrast, a new chromatic aberration correction mechanism is introduced, which makes the image color balanced. The experimental results show that our method can obtain underwater images with enriching texture and harmonious color distribution as compared with other state-of-the-art methods.

Point set registration (PSR) is a crucial problem in computer vision and pattern recognition. Existing PSR methods cannot align point sets robustly due to degradations, such as deformation, noise, occlusion, outlier, and multi-view changes. In this paper, we present a self-selected regularized Gaussian fields criterion for nonrigid point matching. Unlike most existing methods, we formulate the registration problem as a sparse approximation task with low rank constraint in reproducing kernel Hilbert space (RKHS). A self-selected mechanism is used to dynamically assign real-valued label for each point in an accuracy-aware weighting manner, which makes the model focus more on the reliable points in position. Based on the label, an equivalent matching number optimization is embedded into the non-rigid criterion to enhance the reliability of the approximation. Experimental results show that the proposed method can achieve a better result in both registration accuracy and correct matches compared to state-of-the-art approaches.