Hyperspectral (HS) pansharpening is of great importance in improving the spatial resolution of HS images for remote sensing tasks. HS image comprises abundant spectral contents, whereas panchromatic (PAN) image provides spatial information. HS pansharpening constitutes the possibility for providing the pansharpened image with both high spatial and spectral resolution. This article develops a specific pansharpening framework based on a generative dual-adversarial network (called PS-GDANet). Specifically, the pansharpening problem is formulated as a dual task that can be solved by a generative adversarial network (GAN) with two discriminators. The spatial discriminator forces the intensity component of the pansharpened image to be as consistent as possible with the PAN image, and the spectral discriminator helps to preserve spectral information of the original HS image. Instead of designing a deep network, PS-GDANet extends GANs to two discriminators and provides a high-resolution pansharpened image in a fraction of iterations. The experimental results demonstrate that PS-GDANet outperforms several widely accepted state-of-the-art pansharpening methods in terms of qualitative and quantitative assessment.

Image forgeries can entirely change the semantic information of an image, and can be used for unscrupulous purposes. In this paper, we propose a novel image forgery localization network named as MUN, which consists of an M^3 encoder and a UN decoder. Firstly, the M^3 encoder is constructed based on a Multi-scale Max-pooling query module to extract Multi-clue forged features. Noiseprint++ is adopted to assist the RGB clue, and its deployment methodology is discussed. A Multi-scale Max-pooling Query (MMQ) module is proposed to integrate RGB and noise features. Secondly, a novel UN decoder is proposed to extract hierarchical features from both top-down and bottom-up directions, reconstructing both high-level and low-level features at the same time. Thirdly, we formulate an IoU-recalibrated Dynamic Cross-Entropy (IoUDCE) loss to dynamically adjust the weights on forged regions according to IoU which can adaptively balance the influence of authentic and forged regions. Last but not least, we propose a data augmentation method, i.e., Deviation Noise Augmentation (DNA), which acquires accessible prior knowledge of RGB distribution to improve the generalization ability. Extensive experiments on publicly available datasets show that MUN outperforms the state-of-the-art works.

Component substitution (CS) and multiresolution analysis (MRA) based methods have been adopted in hyperspectral pansharpening. The major contribution of this paper is a novel CS-MRA hybrid framework based on intrinsic image decomposition and weighted least squares filter. First, the panchromatic (P) image is sharpened by the Gaussian-Laplacian enhancement algorithm to enhance the spatial details, and the weighted least squares (WLS) filter is performed on the enhanced P image to extract the high-frequency information of the P image. Then, the MTF-based deblurring method is applied to the interpolated hyperspectral (HS) image, and the intrinsic image decomposition (IID) is adopted to decompose the deblurred interpolated HS image into the illumination and reflectance components. Finally, the detail map is generated by making a proper compromise between the high-frequency information of the P image and the spatial information preserved in the illumination component of the HS image. The detail map is further refined by the information ratio of different bands of the HS image and injected into the deblurred interpolated HS image. Experimental results indicate that the proposed method achieves better fusion results than several state-of-the-art hyperspectral pansharpening methods. This demonstrates that a combination of an IID technique and a WLS filter is an effective way for hyperspectral pansharpening.

The application of convolutional neural networks (CNNs) has yielded remarkable outcomes in the fusion of hyperspectral and multispectral images (HSI+MSI). However, most existing researches design black-box models for the direct reconstruction of high-resolution images from low-resolution images, which cannot theoretically guarantee the fusion mechanism throughout the network flow, thus limiting the restoration accuracy. This paper proposes a novel coupled matrix factorization (CMF) constrained deep interpretable network for HSI+MSI fusion, termed as CMF-FUSnet. Specifically, the iterative process of coupled matrix factorization is unfolded into a two-branch network interwoven with multiple denoiser modules and matrix factorization modules. In each iteration, the CMF-encoded two-branch sub-network alternately decomposes HSI and MSI to estimate their abundance and endmember matrices respectively. High-resolution HSI can be obtained by multiplying the endmembers extracted from the HSI and the abundances extracted from the MSI. The benefit is that the proposed CMF-FUSnet breaks through the black-box operation mode while adopting an end-to-end data-driven model, realizes the embedding of physical meaning, and improves the generalization of the model. Numerical experiments show that our proposed CMF-FUSnet compares favorably with both state-of-the-art model-driven and data-driven fusion methods in terms of visual analysis and quality assessment.