In recent years, convolutional neural networks (CNNs) have been increasingly leveraged for the classification of hyperspectral imagery, displaying notable advancements. To address the issues of insufficient spectral and spatial information extraction and high computational complexity in hyperspectral image classification, we introduce the MDRDNet, an integrated neural network model. This novel architecture is comprised of two main components: a Multiscale 3D Depthwise Separable Convolutional Network and a CBAM-augmented Residual Dilated Convolutional Network. The first component employs depthwise separable convolutions in a 3D setting to efficiently capture spatial–spectral characteristics, thus substantially reducing the computational burden associated with 3D convolutions. Meanwhile, the second component enhances the network by integrating the Convolutional Block Attention Module (CBAM) with dilated convolutions via residual connections, effectively counteracting the issue of model degradation. We have empirically evaluated the MDRDNet’s performance by running comprehensive experiments on three publicly available datasets: Indian Pines, Pavia University, and Salinas. Our findings indicate that the overall accuracy of the MDRDNet on the three datasets reached 98.83%, 99.81%, and 99.99%, respectively, which is higher than the accuracy of existing models. Therefore, the MDRDNet proposed in this study can fully extract spatial–spectral joint information, providing a new idea for solving the problem of large model calculations in 3D convolutions.

Hyperspectral images (HSIs) have been broadly applied in remote sensing, environmental monitoring, agriculture, and other fields due to their rich spectral information and complex spatial properties. However, the inherent redundancy, spectral aliasing, and spatial heterogeneity of high-dimensional data pose significant challenges to classification accuracy. Therefore, this study proposes STM-Net, a hybrid deep learning model that integrates SSRE (Spectral–Spatial Residual Extraction Module), Transformer, and MDRM (Multi-scale Differential Residual Module) architectures to comprehensively exploit spectral–spatial features and enhance classification performance. First, the SSRE module employs 3D convolutional layers combined with residual connections to extract multi-scale spectral–spatial features, thereby improving the representation of both local and deep-level characteristics. Second, the MDRM incorporates multi-scale differential convolution and the Convolutional Block Attention Module mechanism to refine local feature extraction and enhance inter-class discriminability at category boundaries. Finally, the Transformer branch equipped with a Dual-Branch Global-Local (DBGL) mechanism integrates local convolutional attention and global self-attention, enabling synergistic optimization of long-range dependency modeling and local feature enhancement. In this study, STM-Net is extensively evaluated on three benchmark HSI datasets: Indian Pines, Pavia University, and Salinas. Additionally, experimental results demonstrate that the proposed model consistently outperforms existing methods regarding OA, AA, and the Kappa coefficient, exhibiting superior generalization capability and stability. Furthermore, ablation studies validate that the SSRE, MDRM, and Transformer components each contribute significantly to improving classification performance. This study presents an effective spectral–spatial feature fusion framework for hyperspectral image classification, offering a novel technical solution for remote sensing data analysis.

High-resolution remote sensing stereo matching is challenging due to heavy computation and the difficulty of handling textureless areas, repetitive structures, and occlusions. To tackle these issues, we design BDNet (Balancing Dual-path Network)—a stereo matching network that seeks a reasonable trade-off between accuracy and efficiency for remote sensing applications. In the feature extraction stage, BDNet adopts progressive dilation with rates 5, 4, and 3, together with a decoupled multi-scale reduction (DMSR) module, which reduces multi-scale feature channels from 320 to 32. We also introduce a strip attention module to make the network more sensitive to horizontal and vertical structures commonly seen in urban scenes. For cost volume construction, the number of correlation groups is lowered from 40 to 8, in line with the compact 32-channel feature representation. For cost aggregation, a dual-path parallel hourglass architecture is designed, which preserves fine details through a high-resolution path while capturing global context through a low-resolution path. An attention-guided fusion module adaptively integrates features from both paths, improving accuracy in challenging regions such as textureless areas and disparity discontinuities. Experiments on the US3D and WHU-Stereo datasets demonstrate that BDNet achieves the best accuracy among the selected baseline methods on US3D, with D1 errors of 16.05% on Jacksonville and 11.84% on Omaha. It requires only 1.43 M parameters and 125.43 G FLOPs, achieving a favorable balance between accuracy and efficiency. Zero-shot generalization experiments on Omaha and WHU-Stereo further suggest the model’s potential for cross-domain adaptation to different satellite sensors and urban scenes.

Aiming at the problems of complex RPC geometric modeling in multi-view stereo matching (MVS) of satellite remote-sensing images, significant feature noise caused by cross-view occlusion and inconsistent lighting, and blurred edge details of height maps, this paper proposes a satellite MVS height estimation network based on a Mamba-enhanced feature pyramid and deformable RPC sampling, MambaDPSMVS. In the feature extraction stage, the cross-view Mamba module and the single-view self-Mamba enhancement module are designed to realize explicit feature interaction between and within views through direction prediction, direction routing, geometric gating fusion and state-space sequence modeling, and suppress view noise from the source. A deformable sampler for an RPC geometry, RPC-DPSampler, is proposed to achieve accurate alignment of source-view features with the reference view through 3D deformable coarse alignment, block sampling, 2D sub-pixel fine-tuning and view-level attention-weighted aggregation. Then, the cascaded cost is constructed, and the loop encoder–decoder regularization is used to complete the height estimation from coarse to fine. Experiments on the WHU-TLC and US3D datasets show that the MAE/RMSE of the proposed method reaches 1.688 m/2.867 m and 1.744 m/3.847 m, respectively, and the PAG_<1m reaches 61.81% and 62.18%, respectively, which values are better than those of baseline methods such as Sat (Red-Net) and Sat (CasMVS-Net). The ablation experiment further validated the complementarity of Mamba enhancement features and the RPC-DPSampler module in feature expression and geometric alignment.