Hyperspectral (HS) pansharpening aims to fuse high-spatial-resolution panchromatic (PAN) images with low-spatial-resolution hyperspectral (LRHS) images to generate high-spatial-resolution hyperspectral (HRHS) images. Due to the lack of consideration for the modal feature difference between PAN and LRHS images, most deep leaning-based methods suffer from spectral and spatial distortions in the fusion results. In addition, most methods use upsampled LRHS images as network input, resulting in spectral distortion. To address these issues, we propose a dual-stage feature correction fusion network (DFCFN) that achieves accurate fusion of PAN and LRHS images by constructing two fusion sub-networks: a feature correction compensation fusion network (FCCFN) and a multi-scale spectral correction fusion network (MSCFN). Based on the lattice filter structure, FCCFN is designed to obtain the initial fusion result by mutually correcting and supplementing the modal features from PAN and LRHS images. To suppress spectral distortion and obtain fine HRHS results, MSCFN based on 2D discrete wavelet transform (2D-DWT) is constructed to gradually correct the spectral features of the initial fusion result by designing a conditional entropy transformer (CE-Transformer). Extensive experiments on three widely used simulated datasets and one real dataset demonstrate that the proposed DFCFN achieves significant improvements in both spatial and spectral quality metrics over other state-of-the-art (SOTA) methods. Specifically, the proposed method improves the SAM metric by 6.4%, 6.2%, and 5.3% compared to the second-best comparison approach on Pavia center, Botswana, and Chikusei datasets, respectively. The codes are made available at: https://github.com/EchoPhD/DFCFN.
In order to solve the problem of interference of ambient light noise in visible light communication (VLC), an adaptive filtering algorithm based on a convolution neural network (CNN) is proposed in this paper. For different channels, CNN is used to learn the relationship between the receiver signal and the original transmitted symbol, and then the received signal is classified using the trained model. Besides, we conducted the VLC experiment to collect data, and the performance of CNN and the least mean square algorithm (LMS) algorithms was compared and analyzed using differential phase shift keying (DPSK) sample data collected through the experiment. The experimental results show that under the same signal-to-noise ratio (SNR), the Bit error rate (BER) of DPSK signal recovery based on CNN is 40% lower than that of the LMS algorithm.
Single hyperspectral image super-resolution aims to reconstruct a high-resolution hyperspectral image (HRHSI) from an observed low resolution hyperspectral image (LRHSI). Most current methods combine CNN and Transformer structures to directly extract features of all channels in LRHSI for image reconstruction, but they do not consider the interference of redundant information in adjacent bands, resulting in spectral and spatial distortions in the reconstruction results and an increase in model computational complexity. To address this issue, this paper proposes a spectral clustering-based pyramid super-resolution network (SCPSN) to progressively reconstruct HRHSI at different scales. In each image reconstruction layer, a clustering super-resolution block (CSRB) consisting of spectral clustering block (SCB), patch non local attention block (PNAB), and dynamic fusion block (DFB) is designed to achieve the reconstruction of detail features. Specifically, for the high correlation between adjacent spectral bands in LRHSI, a SCB is first constructed to achieve clustering of spectral channels and filtering of hyperchannels. This can reduce the interference of redundant spectral information and the computational complexity of the model. Then, by utilizing the non-local similarity of features within the channel, a patch non-local attention block (PNAB) is constructed to enhance the features of hyperchannels. Next, a dynamic fusion block (DFB) is designed to reconstruct the features of all channels in LRHSI by establishing correlations between enhanced hyperchannels and other channels. Finally, the reconstructed channels are upsampled and added to the corresponding channels to obtain the reconstructed HRHSI. Extensive experiments validate that the performance of SCPSN is superior to that of some other state-of-the-art (SOTA) HSSR methods in terms of visual effects and quantitative metrics. In addition, our model does not require training on large-scale datasets compared to other methods. The dataset and code will be released on GitHub.
10 June 2026 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Pansharpening aims to fuse panchromatic (PAN) images and low-resolution multispectral (LRMS) images to generate high-resolution multispectral (HRMS) images. Existing deep learning-based methods often overlook the pixel-level differences between these images, leading to inaccurate feature representation and limited fusion performance. To address this issue, this paper proposes a spatial-spectral difference prior guided network (SSDP-Net) for pansharpening. Its core idea is to explicitly model and utilize the spatial and spectral differences between PAN and LRMS images, and treat these differences as prior information to guide accurate feature learning. The network adopts a multi-branch architecture to separately model spatial and spectral features, and realizes hierarchical fusion of complementary information across multiple scales. This design not only ensures the effective preservation of spatial details but also maintains the spectral consistency of the fusion results. Extensive experimental results on multiple datasets show that the proposed SSDP-Net achieves excellent fusion performance with high spatial and spectral fidelity, outperforming various state-of the-art methods in both quantitative and qualitative evaluations. The source code of this work will be released on GitHub.
1 May 2026 in Journal of Computer Science and Technology