High-resolution Panchromatic Image Research Articles

Frequency-Adaptive Pan-Sharpening with Mixture of Experts

Pan-sharpening involves reconstructing missing high-frequency information in multi-spectral images with low spatial resolution, using a higher-resolution panchromatic image as guidance. Although the inborn connection with frequency domain, existing pan-sharpening research has not almost investigated the potential solution upon frequency domain. To this end, we propose a novel Frequency Adaptive Mixture of Experts (FAME) learning framework for pan-sharpening, which consists of three key components: the Adaptive Frequency Separation Prediction Module, the Sub-Frequency Learning Expert Module, and the Expert Mixture Module. In detail, the first leverages the discrete cosine transform to perform frequency separation by predicting the frequency mask. On the basis of generated mask, the second with low-frequency MOE and high-frequency MOE takes account for enabling the effective low-frequency and high-frequency information reconstruction. Followed by, the final fusion module dynamically weights high frequency and low-frequency MOE knowledge to adapt to remote sensing images with significant content variations. Quantitative and qualitative experiments over multiple datasets demonstrate that our method performs the best against other state-of-the-art ones and comprises a strong generalization ability for real-world scenes. Code will be made publicly at https://github.com/alexhe101/FAME-Net.

Unsupervised Pan-Sharpening via Mutually Guided Detail Restoration

Pan-sharpening is a task that aims to super-resolve the low-resolution multispectral (LRMS) image with the guidance of a corresponding high-resolution panchromatic (PAN) image. The key challenge in pan-sharpening is to accurately modeling the relationship between the MS and PAN images. While supervised deep learning methods are commonly employed to address this task, the unavailability of ground-truth severely limits their effectiveness. In this paper, we propose a mutually guided detail restoration method for unsupervised pan-sharpening. Specifically, we treat pan-sharpening as a blind image deblurring task, in which the blur kernel can be estimated by a CNN. Constrained by the blur kernel, the pan-sharpened image retains spectral information consistent with the LRMS image. Once the pan-sharpened image is obtained, the PAN image is blurred using a pre-defined blur operator. The pan-sharpened image, in turn, is used to guide the detail restoration of the blurred PAN image. By leveraging the mutual guidance between MS and PAN images, the pan-sharpening network can implicitly learn the spatial relationship between the two modalities. Extensive experiments show that the proposed method significantly outperforms existing unsupervised pan-sharpening methods.

Assessing the Efficacy of Pixel-Level Fusion Techniques for Ultra-High-Resolution Imagery: A Case Study of BJ-3A.

Beijing Satellite 3 is a high-performance optical remote sensing satellite with a spatial resolution of 0.3-0.5 m. It can provide timely and independent ultra-high-resolution spatial big data and comprehensive spatial information application services. At present, there is no relevant research on the fusion method of BJ-3A satellite images. In many applications, high-resolution panchromatic images alone are insufficient. Therefore, it is necessary to fuse them with multispectral images that contain spectral color information. Currently, there is a lack of research on the fusion method of BJ-3A satellite images. This article explores six traditional pixel-level fusion methods (HPF, HCS, wavelet, modified-IHS, PC, and Brovey) for fusing the panchromatic image and multispectral image of the BJ-3A satellite. The fusion results were analyzed qualitatively from two aspects: spatial detail enhancement capability and spectral fidelity. Five indicators, namely mean, standard deviation, entropy, correlation coefficient, and average gradient, were used for quantitative analysis. Finally, the fusion results were comprehensively evaluated from three aspects: spectral curves of ground objects, absolute error figure, and object-oriented classification effects. The findings of the research suggest that the fusion method known as HPF is the optimum and appropriate technique for fusing panchromatic and multispectral images obtained from BJ-3A. These results can be utilized as a guide for the implementation of BJ-3A panchromatic and multispectral data fusion in real-world scenarios.

Hyperspectral low altitude UAV target tracking algorithm based on deep learning and improved KCF

This article presents a novel target tracking algorithm for hyperspectral low altitude UAV, combining deep learning with an improved Kernelized Correlation Filter (KCF). Initially, an image noise reduction method based on principal component analysis with Block-Matching 3D (BM3D), is employed to process redundant information. Subsequently, an image fusion method is utilized to merge the processed hyperspectral image and the high-resolution panchromatic band image to obtain a high spatial resolution image for target enhancement. Following this, YOLOv5 is used to detect the coordinate information of the UAV target in the current frame. Then, The KCF algorithm is used for target tracking in the current frame using kernel correlation filtering. Finally, the Discriminative Scale Spatial Tracker (DSST) is employed to determine the scale information to achieve a multi-scale tracking effect. The experimental results demonstrate that the algorithm presented in this paper surpasses CSK, HLT, and the conventional KCF algorithm in hyperspectral UAV datasets. On average, there is a significant increase in accuracy which is over 17% when using our algorithm.

AB-PLS-DA: Pansharpening tailored for Scanning Electron Microscopy and Energy-Dispersive X-ray Spectrometry multimodal fusion

Pansharpening constitutes a category of data fusion techniques designed to enhance the spatial resolution of multispectral (MS) images by integrating spatial details from a high-resolution panchromatic (PAN) image. This process combines the high-spectral data of MS images with the rich spatial information of the PAN image, resulting in a pansharpened output ideal for more effective image analysis, such as object detection and environmental monitoring. Traditionally developed for satellite data, our paper introduces a novel pansharpening approach customized for the fusion of Scanning Electron Microscopy (SEM) and Energy-Dispersive X-ray Spectrometry (EDS) data. The proposed method, grounded in Partial Least Squares regression with Discriminant Analysis (PLS-DA), significantly boosts the spatial resolution of EDS data while preserving spectral details. A key feature of this approach involves partitioning the PAN image into intensity bins and dynamically adapting this division in cases of overlapping compounds with similar average atomic numbers. We evaluate the method’s effectiveness using in-house EDS images obtained from both even and uneven sample surfaces. Comparative analysis against existing benchmarks and state-of-the-art pansharpening techniques demonstrates superior performance in both spectral and spatial quality indicators for our method.

ZeRGAN: Zero-Reference GAN for Fusion of Multispectral and Panchromatic Images.

In this article, we present a new pansharpening method, a zero-reference generative adversarial network (ZeRGAN), which fuses low spatial resolution multispectral (LR MS) and high spatial resolution panchromatic (PAN) images. In the proposed method, zero-reference indicates that it does not require paired reduced-scale images or unpaired full-scale images for training. To obtain accurate fusion results, we establish an adversarial game between a set of multiscale generators and their corresponding discriminators. Through multiscale generators, the fused high spatial resolution MS (HR MS) images are progressively produced from LR MS and PAN images, while the discriminators aim to distinguish the differences of spatial information between the HR MS images and the PAN images. In other words, the HR MS images are generated from LR MS and PAN images after the optimization of ZeRGAN. Furthermore, we construct a nonreference loss function, including an adversarial loss, spatial and spectral reconstruction losses, a spatial enhancement loss, and an average constancy loss. Through the minimization of the total loss, the spatial details in the HR MS images can be enhanced efficiently. Extensive experiments are implemented on datasets acquired by different satellites. The results demonstrate that the effectiveness of the proposed method compared with the state-of-the-art methods. The source code is publicly available at https://github.com/RSMagneto/ZeRGAN.

GDF: A Novel Image Fusion Approach for Compelling Depiction of Earthly Features

One of the most challenging aspects of satellite remote sensing is image fusion. Image fusion increases the visual interpretation of the image and has many applications such as monitoring water bodies, land cover, urbanisation, agriculture, national defence, and so forth. Remote sensing applications require images with a high spatial and spectral resolution for accurately processing and distinguishing the land cover classes with fine texture and shape details. Due to technical limitations, most satellites cannot take high-resolution multi-spectral images but can get high-resolution panchromatic images and low-resolution multi-spectral satellite images separately. This article proposes a novel fusion method, geospatial data fusion (GDF), to obtain high-resolution multi-spectral images. GDF, along with three well-known fusion methods viz., Brovey Transform (BT), wavelet transform (WT), and Fourier transform (FT), have been comparatively implemented to fuse the Cartosat-2 and Sentinel-2 imageries of the Sangam area of Prayagraj, India. The fusion has been done to extract the earth’s surface features from the fused imagery. In this research, the fused image is utilised for river water mapping. Results confirm that the GDF outperforms other existing fusion methods and successfully maps the river water in the study area.

A Swin Transformer with Dynamic High-Pass Preservation for Remote Sensing Image Pansharpening

Pansharpening is a technique used in remote sensing to combine high-resolution panchromatic (PAN) images with lower resolution multispectral (MS) images to generate high-resolution multispectral images while preserving spectral characteristics. Recently, convolutional neural networks (CNNs) have been the mainstream in pansharpening by extracting the deep features of PAN and MS images and fusing these abstract features to reconstruct high-resolution details. However, they are limited by the short-range contextual dependencies of convolution operations. Although transformer models can alleviate this problem, they still suffer from weak capability in reconstructing high-resolution detailed information from global representations. To this end, a novel Swin-transformer-based pansharpening model named SwinPAN is proposed. Specifically, a detail reconstruction network (DRNet) is developed in an image difference and residual learning framework to reconstruct the high-resolution detailed information from the original images. DRNet is developed based on the Swin Transformer with a dynamic high-pass preservation module with adaptive convolution kernels. The experimental results on three remote sensing datasets with different sensors demonstrate that the proposed approach performs better than state-of-the-art networks through qualitative and quantitative analysis. Specifically, the generated pansharpening results contain finer spatial details and richer spectral information than other methods.

Zero-shot semi-supervised learning for pansharpening

Pansharpening refers to fusing a low-resolution multispectral image (LRMS) and a high-resolution panchromatic (PAN) image to generate a high-resolution multispectral image (HRMS). Traditional pansharpening methods use a single pair of LRMS and PAN to generate HRMS at full resolution, but they fail to generate high-quality fused products due to the assumption of a (often inaccurate) linear relationship between the fused products. Convolutional neural network methods, i.e., supervised and unsupervised learning approaches, can model any arbitrary non-linear relationship among data, but performing even worse than traditional methods when testing data are not consistent with training data. Moreover, supervised methods rely on simulating reduced resolution data for training causing information loss at full resolution. Unsupervised pansharpening suffers from distortion due to the lack of reference images and inaccuracy in the estimation of the degradation process. In this paper, we propose a zero-shot semi-supervised method for pansharpening (ZS-Pan), which only requires a single pair of PAN/LRMS images for training and testing networks combining both the pros of supervised and unsupervised methods. Facing with challenges of limited training data and no reference images, the ZS-Pan framework is built with a two-phase three-component model, i.e., the reduced resolution supervised pre-training (RSP), the spatial degradation establishment (SDE), and the full resolution unsupervised generation (FUG) stages. Specifically, a special parameter initialization technique, a data augmentation strategy, and a non-linear degradation network are proposed to improve the representation ability of the network. In our experiments, we evaluate the performance of the proposed framework on different datasets using some state-of-the-art (SOTA) pansharpening approaches for comparison. Results show that our ZS-Pan outperforms these SOTA methods, both visually and quantitatively. The code is available at https://github.com/coder-qicao/ZS-Pan.

Zero-Sharpen: A universal pansharpening method across satellites for reducing scale-variance gap via zero-shot variation

Pansharpening is a technique that combines a high-resolution panchromatic image (HRPAN) and a low-resolution multi-spectral image (LRMS) to generate a high-resolution multi-spectral image (HRMS). Traditional methods perform sharpening based on given image pairs, but their performance is limited due to the employment of scale-varying linear mapping assumptions. Existing deep-learning-based methods can establish arbitrary non-linear sharpening functions based on large-scale training data. However, supervised methods suffer from scale-variance generalization for training on the simulated reduced resolution data, while unsupervised methods arise distortion for the absence of reference and introduction of inaccurate spectral observation assumptions. Besides, the generic satellite-specific learning (i.e. training and testing on the homologous satellite data) causes low generalization when processing the heterologous satellite data. To this end, we combine the advantages of deep learning and variational optimization, to propose a universal pansharpening method that can be applied across different satellites with reducing the scale variance, termed as Zero-Sharpen. On the one hand, we build image-pair-specific neural networks to extend the spatial mapping and spectral observation assumptions to the nonlinear space. These assumptions are incorporated as deep spatial prior and deep spectral observation prior for regularization, assisting variational models to iteratively adapt to the full-resolution scale. On the other hand, the variational optimization mechanism also promotes the optimization of deep networks so as to achieve the preservation of spectral and spatial information in a zero-shot learning manner. In doing so, our method can be easily available across different satellites. Extensive experiments demonstrate the superiority of our method over the state-of-the-art methods both qualitatively and quantitatively. Code is publicly available at https://github.com/Baixuzx7/ZeroSharpen.

Swin–MRDB: Pan-Sharpening Model Based on the Swin Transformer and Multi-Scale CNN

Pan-sharpening aims to create high-resolution spectrum images by fusing low-resolution hyperspectral (HS) images with high-resolution panchromatic (PAN) images. Inspired by the Swin transformer used in image classification tasks, this research constructs a three-stream pan-sharpening network based on the Swin transformer and a multi-scale feature extraction module. Unlike the traditional convolutional neural network (CNN) pan-sharpening model, we use the Swin transformer to establish global connections with the image and combine it with a multi-scale feature extraction module to extract local features of different sizes. The model combines the advantages of the Swin transformer and CNN, enabling fused images to maintain good local detail and global linkage by mitigating distortion in hyperspectral images. In order to verify the effectiveness of the method, this paper evaluates fused images with subjective visual and quantitative indicators. Experimental results show that the method proposed in this paper can better preserve the spatial and spectral information of images compared to the classical and latest models.

A pan-sharpening network using multi-resolution transformer and two-stage feature fusion.

Pan-sharpening is a fundamental and crucial task in the remote sensing image processing field, which generates a high-resolution multi-spectral image by fusing a low-resolution multi-spectral image and a high-resolution panchromatic image. Recently, deep learning techniques have shown competitive results in pan-sharpening. However, diverse features in the multi-spectral and panchromatic images are not fully extracted and exploited in existing deep learning methods, which leads to information loss in the pan-sharpening process. To solve this problem, a novel pan-sharpening method based on multi-resolution transformer and two-stage feature fusion is proposed in this article. Specifically, a transformer-based multi-resolution feature extractor is designed to extract diverse image features. Then, to fully exploit features with different content and characteristics, a two-stage feature fusion strategy is adopted. In the first stage, a multi-resolution fusion module is proposed to fuse multi-spectral and panchromatic features at each scale. In the second stage, a shallow-deep fusion module is proposed to fuse shallow and deep features for detail generation. Experiments over QuickBird and WorldView-3 datasets demonstrate that the proposed method outperforms current state-of-the-art approaches visually and quantitatively with fewer parameters. Moreover, the ablation study and feature map analysis also prove the effectiveness of the transformer-based multi-resolution feature extractor and the two-stage fusion scheme.

Fusion Approaches to Individual Tree Species Classification Using Multisource Remote Sensing Data

With the wide availability of remotely sensed data from various sensors, fusion-based tree species classification approaches have emerged as a prominent and ongoing research topic. However, most recent studies primarily focused on combining multisource data at the feature level, while few systematically examined their positive or negative contributions to tree species classification. This study aimed to investigate fusion approaches at the feature and decision levels deployed with support vector machine and random forest algorithms to classify five dominant tree species: Norway maple, honey locust, Austrian pine, white spruce, and blue spruce in individual crowns. Spectral, textural, and structural features derived from multispectral imagery (MSI), a very high-resolution panchromatic image (PAN), and LiDAR data were systematically exploited to assess their contributions to accurate classifications. Among the various classification schemes that were explored, both feature- and decision-level fusion approaches demonstrated significant improvements in tree species classification compared with the utilization of MSI (0.7), PAN (0.74), or LiDAR (0.8) in isolation. Notably, the decision-level fusion approach achieved the highest overall accuracies (0.86 for SVM and 0.84 for RF) and kappa coefficients (0.82 for SVM and 0.79 for RF). The misclassification analysis of fusion approaches highlighted the potential and flexibility of decision-level fusion in tree species classification.

A image fusion and U-Net approach to improving crop planting structure multi-category classification in irrigated area

Some subtle features of planting structures in irrigation areas could only be visible on high-resolution panchromatic spectral images. However, low spatial resolution multispectral image makes it hard to recognize them. It is challenging to accurately obtain crop planting structure when using traditional methods. This paper proposes an extraction method of crop planting structure based on image fusion and U-Net depth semantic segmentation network, which can automatically and accurately extract multi-category crop planting structure information. This method takes Landsat8 commercial multispectral satellite data set as an example, chooses RGB pseudo-color synthetic image which highlights vegetation characteristics, and uses HLS(Hue, Luminance, Saturation), NND(Nearest-Neighbor Diffusion) and G-S(Gram-Schmidt) methods to fuse panchromatic band to obtain 15m high-resolution fusion image to obtain training set and test set, six types of land features including cities and rivers were labeled by manual to obtain the verification set. The training and validation sets are cut and enhanced to train the U-Net semantic segmentation network. Taking the Xiaokaihe irrigation area in Binzhou City, Shandong Province, China, as an example, the planting structure was classified, and the overall accuracy was 87.7%, 91.2%, and 91.3%, respectively. The accuracy of crop planting structures (wheat, cotton, woodland) was 74.2%, 82.5%, 82.3%, and the Kappa coefficient was 0.832, 0.880, and 0.881, respectively. The results showed that the NND-UNet method was suitable for large-scale continuous crop types (wheat, cotton), and the GS-UNet method had a better classification effect in discrete areas of cash crops (Jujube and many kinds of fruit trees).

Pansharpening Model of Transferable Remote Sensing Images Based on Feature Fusion and Attention Modules

The purpose of the panchromatic sharpening of remote sensing images is to generate high-resolution multispectral images through software technology without increasing economic expenditure. The specific method is to fuse the spatial information of a high-resolution panchromatic image and the spectral information of a low-resolution multispectral image. This work proposes a novel model for generating high-quality multispectral images. This model uses the feature domain of the convolution neural network to fuse multispectral and panchromatic images so that the fused images can generate new features so that the final fused features can restore clear images. Because of the unique feature extraction ability of convolution neural networks, we use the core idea of convolution neural networks to extract global features. To extract the complementary features of the input image at a deeper level, we first designed two subnetworks with the same structure but different weights, and then used single-channel attention to optimize the fused features to improve the final fusion performance. We select the public data set widely used in this field to verify the validity of the model. The experimental results on the GaoFen-2 and SPOT6 data sets show that this method has a better effect in fusing multi-spectral and panchromatic images. Compared with the classical and the latest methods in this field, our model fusion obtained panchromatic sharpened images from both quantitative and qualitative analysis has achieved better results. In addition, to verify the transferability and generalization of our proposed model, we directly apply it to multispectral image sharpening, such as hyperspectral image sharpening. Experiments and tests have been carried out on Pavia Center and Botswana public hyperspectral data sets, and the results show that the model has also achieved good performance in hyperspectral data sets.

DICO: Dingo coot optimization-based ZF net for pansharpening

With the recent advancements in technology, there has been a tremendous growth in the usage of images captured using satellites in various applications, like defense, academics, resource exploration, land-use mapping, and so on. Certain mission-critical applications need images of higher visual quality, but the images captured by the sensors normally suffer from a tradeoff between high spectral and spatial resolutions. Hence, for obtaining images with high visual quality, it is necessary to combine the low resolution multispectral (MS) image with the high resolution panchromatic (PAN) image, and this is accomplished by means of pansharpening. In this paper, an efficient pansharpening technique is devised by using a hybrid optimized deep learning network. Zeiler and Fergus network (ZF Net) is utilized for performing the fusion of the sharpened and upsampled MS image with the PAN image. A novel Dingo coot (DICO) optimization is created for updating the learning parameters and weights of the ZF Net. Moreover, the devised DICO_ZF Net for pansharpening is examined for its effectiveness by considering measures, like Peak Signal To Noise Ratio (PSNR) and Degree of Distortion (DD) and is found to have attained values at 50.177 dB and 0.063 dB.

Spatial-Spectral Dual Back-Projection Network for Pansharpening

Deep unfolding networks have obtained satisfactory performance in the pansharpening task owing to their sufficient interpretability. Inspired by the back-projection (BP) mechanism, we propose a BP-driven model, spatial-spectral dual back-project network (S <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> DBPN), to fuse the low spatial resolution multispectral (LR MS) and the high spatial resolution panchromatic (PAN) images by exploiting the BP in spatial and spectral domains. Specifically, the proposed S <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> DBPN is made up of a spatial BP network, a spectral BP network, and a reconstruction network. In the spatial BP network, spatial down- and up-projection modules are derived from BP, which is responsible for the projection of the LR MS image into the spatial domain. By analogy with the spatial BP, we reformulate the degradation between high spatial resolution multispectral (HR MS) and PAN images as spectral down- and up-projections. Then, the spectral BP network is constructed for the projection of the PAN image along the channel dimension. Finally, the features from spatial and spectral BP networks are integrated to produce the desired HR MS image through the reconstruction network. Compared to the state-of-the-art methods, extensive experiments on QuickBird, GeoEye-1, and WorldView-2 datasets demonstrate that our S <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> DBPN produces better HR MS images in terms of qualitative and quantitative evaluation metrics. The code of S <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> DBPN is released at: https://github.com/RSMagneto/S2DBPN.

Multiresolution Analysis Pansharpening Based on Variation Factor for Multispectral and Panchromatic Images From Different Times

Most pansharpening methods refer to the fusion of the original low-resolution multispectral (MS) and high-resolution panchromatic images (PAN) acquired simultaneously over the same area. Due to its good robustness, multiresolution analysis (MRA) has become one of the important categories of pansharpening methods. However, when only MS and PAN images acquired at different times can be provided, the fusion results from current MRA methods are often not ideal due to the failure to effectively analyze multitemporal misalignments between MS and PAN images from different times. To solve this issue, MRA pansharpening based on variation factor for MS and PAN images from different times is proposed. The multi-resolution analysis pansharpening based on dual-scale regression model is first established, and the variation factor is then introduced to effectively analyze the multitemporal misalignments by using alternating direction method of multipliers (ADMM), yielding the final fusion results. Experiments with synthetic and real datasets show that the proposed method exhibits significant performance improvement compared to the traditional pansharpening methods, as well as the state-of-the-art MRA methods. Visual comparisons demonstrate that the variation factor introduces encouraging improvements in the compensation of multi-temporal misalignments in ground objects and advances pansharpening applications for MS and PAN images acquired at different times.

Pansharpening via Frequency-Aware Fusion Network With Explicit Similarity Constraints

The process of fusing a high spatial resolution (HR) panchromatic (PAN) image and a low spatial resolution (LR) multispectral (MS) image to obtain an HRMS image is known as pansharpening. With the development of convolutional neural networks, the performance of pansharpening methods has been improved, however, the blurry effects and the spectral distortion still exist in their fusion results due to the insufficiency in details learning and the frequency mismatch between MS and PAN. Therefore, the improvement of spatial details at the premise of reducing spectral distortion is still a challenge. In this paper, we propose a frequency-aware fusion network (FAFNet) together with a novel high-frequency feature similarity loss to address above mentioned problems. FAFNet is mainly composed of two kinds of blocks, where the frequency aware blocks aim to extract features in the frequency domain with the help of discrete wavelet transform (DWT) layers, and the frequency fusion blocks reconstruct and transform the features from frequency domain to spatial domain with the assistance of inverse DWT (IDWT) layers. Finally, the fusion results are obtained through a convolutional block. In order to learn the correspondence, we also propose a high-frequency feature similarity loss to constrain the HF features derived from PAN and MS branches, so that HF features of PAN can reasonably be used to supplement that of MS. Experimental results on three datasets at both reduced- and full-resolution demonstrate the superiority of the proposed method compared with several state-of-the-art pansharpening models. The codes are available at https://github.com/YinghuiXing/FAFNet.

PanDiff: A Novel Pansharpening Method Based on Denoising Diffusion Probabilistic Model

Pansharpening is a crucial image processing technique for numerous remote sensing downstream tasks, aiming to recover high spatial resolution multispectral (HRMS) images by fusing high spatial resolution panchromatic (PAN) images and low spatial resolution multispectral (LRMS) images. Most current mainstream pansharpening fusion frameworks directly learn the mapping relationships from PAN and LRMS images to HRMS images by extracting key features. However, we propose a novel pansharpening method based on the denoising diffusion probabilistic model (DDPM) called PanDiff, which learns the data distribution of the difference maps (DM) between HRMS and interpolated MS (IMS) images from a new perspective. Specifically, PanDiff decomposes the complex fusion process of PAN and LRMS images into a multi-step Markov process, and the U-Net is employed to reconstruct each step of the process from random Gaussian noise. Notably, the PAN and LRMS images serve as the injected conditions to guide the U-Net in PanDiff, rather than being the fusion objects as in other pansharpening methods. Furthermore, we propose a modal intercalibration module (MIM) to enhance the guidance effect of the PAN and LRMS images. The experiments are conducted on a freely available benchmark dataset, including GaoFen-2, QuickBird, and WorldView-3 images. The experimental results from the fusion and generalization tests effectively demonstrate the outstanding fusion performance and high robustness of PanDiff. Fig. 1 depicts the results of the proposed method performed on various scenes. Additionally, the ablation experiments confirm the rationale behind PanDiff’s construction.