Multimodal image fusion involves tasks like pan-sharpening and depth super-resolution. Both tasks aim to generate high-resolution target images by fusing the complementary information from the texture-rich guidance and low-resolution target counterparts. They are inborn with reconstructing high-frequency information. Despite their inherent frequency domain connection, most existing methods only operate solely in the spatial domain and rarely explore the solutions in the frequency domain. This study addresses this limitation by proposing solutions in both the spatial and frequency domains. We devise a Spatial-Frequency Information Integration Network, abbreviated as SFINet for this purpose. The SFINet includes a core module tailored for image fusion. This module consists of three key components: a spatial-domain information branch, a frequency-domain information branch, and a dual-domain interaction. The spatial-domain information branch employs the spatial convolution-equipped invertible neural operators to integrate local information from different modalities in the spatial domain. Meanwhile, the frequency-domain information branch adopts a modality-aware deep Fourier transformation to capture the image-wide receptive field for exploring global contextual information. In addition, the dual-domain interaction facilitates information flow and the learning of complementary representations. We further present an improved version of SFINet, SFINet++, that enhances the representation of spatial information by replacing the basic convolution unit in the original spatial domain branch with the information-lossless invertible neural operator. We conduct extensive experiments to validate the effectiveness of the proposed networks and demonstrate their outstanding performance against state-of-the-art methods in two representative multimodal image fusion tasks: pan-sharpening and depth super-resolution.

The goal of pan-sharpening is to produce a high-spatial-resolution multi-spectral (HRMS) image from a low-spatial-resolution multi-spectral (LRMS) counterpart by super-resolving the LRMS one under the guidance of a texture-rich panchromatic (PAN) image. Existing research has concentrated on using spatial information to generate HRMS images, but has neglected to investigate the frequency domain, which severely restricts the performance improvement. In this work, we propose a novel pan-sharpening approach, named Multi-Scale Dual-Domain Guidance Network (MSDDN) by fully exploring and exploiting the distinguished information in both the spatial and frequency domains. Specifically, the network is inborn with multi-scale U-shape manner and composed by two core parts: a spatial guidance sub-network for fusing local spatial information and a frequency guidance sub-network for fusing global frequency domain information and encouraging dual-domain complementary learning. In this way, the model can capture multi-scale dual-domain information to help it generate high-quality pan-sharpening results. Employing the proposed model on different datasets, the quantitative and qualitative results demonstrate that our method performs appreciatively against other state-of-the-art approaches and comprises a strong generalization ability for real-world scenes. The source code is available at https://github.com/alexhe101/MSDDN.

Pan-sharpening is essentially a panchromatic (PAN)-guided super-resolution process, primarily focused on enhancing multi-spectral image quality. This methodology intricately incorporates the high-frequency derived from texture-rich PAN images into the lower-resolution multi-spectral (LRMS) counterparts. However, current spatial domain techniques frequently face challenges in accurately restoring texture details, while frequency domain methods lack efficient interaction with spatial domains, thus restricting the overall model performance. In response to these challenges, we introduce a novel High-frequency Wavelet Network that capitalizes on the spatial-frequency interaction and frequency division capabilities inherent in wavelet transform. In particular, our approach consists of two fundamental modules: the Wavelet-Inspired Fusion Block and the High-Frequency Enhancement Block. The former is inspired by wavelet lifting schemes, enabling the fusion of frequencies and facilitating information exchange across various subbands. The latter harnesses wavelet’s frequency division attributes to enhance high-frequency information learning. Comprehensive experiments over multiple satellite datasets demonstrate that our approach outperforms state-of-the-art techniques in both quantitative and qualitative assessments. Moreover, our model showcases exceptional generalization capabilities in real-world scenarios. Code is available at https://github.com/alexhe101/WINet.

Due to the physical hardware limits, multi-spectral (MS) images often suffer from low-spatial resolution, challenging their practical utility in real applications. Therefore, pan-sharpening technology has been widely explored as a popular tool to generate images with both high-spatial and high-spectral resolutions by integrating PAN and MS images. In this paper, we propose an effective pan-sharpening network, which consists of two core designs: a PAN-guided band-aware multi-spectral feature enhancement module and a multi-focus feature fusion module. To be specific, the former exploits the PAN features to perform band-aware multi-spectral feature modulation and selectively enhance the information of each spectral band while the latter covers various convolution kernels to extract multi-scale features, benefiting the fusion performance of the remote sensing scene. Equipped with the above core modules, our proposed framework is capable of achieving the best performance when compared with existing state-of-the-art Pan-sharpening methods over multiple satellite datasets. Extensive ablation studies are additionally conducted to verify the effectiveness of our key components both visually and quantitatively.

In this article, we propose a novel graph convolutional network (GCN) for pansharpening, defined as GCPNet, which consists of three main modules: the spatial GCN module (SGCN), the spectral band GCN module (BGCN), and the atrous spatial pyramid module (ASPM). Specifically, due to the nature of GCN, the proposed SGCN and BGCN are capable of exploring the long-range relationship between the object and the global state in the spatial and spectral aspects, which benefits pansharpened results and has not been fully investigated before. In addition, the designed ASPM is equipped with multiscale atrous convolutions and learns richer local feature information, so as to cover the objects of different sizes in satellite images. To further enhance the representation of our proposed GCPNet, asynchronous knowledge distillation is introduced to provide compact features by heterogeneous task imitation in a teacher–student paradigm. In the paradigm, the teacher network acts as a variational autoencoder to extract compact features of the ground-truth MS images. The student network, devised for pansharpening, is trained with the assistance of the teacher network to transfer the important information of the expected ground-truth MS images. Extensive experimental results on different satellite datasets demonstrate that our proposed network outperforms the state-of-the-art methods both visually and quantitatively. The source code is released at https://github.com/Keyu-Yan/GCPNet .