ISPRS Journal of Photogrammetry and Remote Sensing最新文献

{"title":"3D building reconstruction from monocular remote sensing imagery via diffusion models and geometric priors","authors":"Zhenghao Hu,&nbsp;Weijia Li,&nbsp;Jinhua Yu,&nbsp;Minfa Liu,&nbsp;Junyan Ye,&nbsp;Peimin Chen,&nbsp;Huabing Huang","doi":"10.1016/j.isprsjprs.2025.11.018","DOIUrl":"10.1016/j.isprsjprs.2025.11.018","url":null,"abstract":"<div><div>3D building reconstruction from monocular remote sensing imagery has emerged as a critical research topic due to its cost-effective data acquisition and scalability for large-area applications. However, the reconstruction accuracy of existing methods remains limited due to suboptimal performance in both contour extraction and height estimation. The limited feature extraction capabilities of the models and the difficulty in differentiating building roofs from facades collectively restrict the accuracy of reconstructed contours in existing methods. Meanwhile, building height estimation remains particularly challenging in monocular images due to the limited information from a single perspective. To address these challenges, we propose DG-BRF, a Diffusion-Geometric based Building Reconstruction Framework that integrates a diffusion-model-based roof and facade segmentation network with a geometric prior-driven offset calculation method for precise 3D reconstruction from monocular remote sensing images. To improve the accuracy of building contour extraction, we design an effective diffusion-model-based roof and facade segmentation network and improve roof-facade differentiation by novelly incorporating a depth-aware encoder. Moreover, unlike conventional methods that rely on challenging height regression, we propose a geometric prior-driven offset calculation method, strategically converting the challenging height regression problem into a simple roof-facade matching task. Experimental results on two newly proposed 3D reconstruction datasets demonstrate the effectiveness of our framework. DG-BRF achieves superior performance, outperforming the current state-of-the-art by 3% and 13% in height estimation accuracy and 3% and 6% in footprint segmentation F1-score, demonstrating its capability to overcome the limitations of existing methods and offer a novel solution for 3D building reconstruction from monocular remote sensing images. The dataset and source code of this work will be available at <span><span>https://github.com/zhenghaohu/DG-BRF</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"232 ","pages":"Pages 124-137"},"PeriodicalIF":12.2,"publicationDate":"2025-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145684929","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cross-satellite hierarchical multimodal denoising for hyperspectral imagery","authors":"Minghua Wang ,&nbsp;Bo Shang ,&nbsp;Yilun Li ,&nbsp;Xin Zhao ,&nbsp;Lianru Gao ,&nbsp;Xu Sun ,&nbsp;Longfei Ren","doi":"10.1016/j.isprsjprs.2025.11.028","DOIUrl":"10.1016/j.isprsjprs.2025.11.028","url":null,"abstract":"<div><div>The rapid proliferation of remote sensing satellite constellations has ushered in an era of unprecedented access to hyperspectral (HS) and multispectral (MS) Earth observation data. HS denoising remains a critical research focus for enhancing the interpretation and application of satellite data. However, on the one hand, the available characteristics of noisy HS satellite data are often limited under real-world and unknown conditions. On the other hand, existing works ignore the complementary advantages offered by MS satellite imagery that can be employed to enhance HS denoising performance. Leveraging the synergistic potential of HS and MS data, this study pioneers a novel paradigm for the joint exploitation and optimization of multi-source remote sensing satellites. A novel Hierarchical Dual Tucker Decomposition (DTucker) framework is proposed to capitalize on the low-rank (LR) tensor property of HS and MS cross-satellite data. The inheritance of properties from the original tensor to the core tensor is explored through a manually designed model-driven constraint or a data-driven multilayer perceptron (MLP) framework. This enables robust integration of MS-derived spatial richness with HS details and significantly enhances the denoising capability. We construct HS–MS data pairs from real satellite observations, including Earth Observing-1, Sentinel-2, Gaofen-1, Gaofen-5, and Gaofen-6. Four datasets span diverse scenes such as runways, urban areas, rivers, and farmlands. The proposed method demonstrates strong generalization across various satellite combinations and application scenarios. Notably, the incorporation of MS data markedly enhances both class discrimination and structural detail in the denoised HS outputs, promoting the performance of subsequent classification and analysis tasks. The datasets and codes implemented in MATLAB and PYTHON will be available on the website: <span><span>https://github.com/MinghuaWang123/DTucker</span><svg><path></path></svg></span>, contributing to the remote sensing community.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"232 ","pages":"Pages 94-108"},"PeriodicalIF":12.2,"publicationDate":"2025-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145684885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Extrapolate azimuth angles: Text and edge guided ISAR image generation based on foundation model","authors":"Jiawei Zhang,&nbsp;Xiaolin Zhou,&nbsp;Weidong Jiang,&nbsp;Xiaolong Su,&nbsp;Zhen Liu,&nbsp;Li Liu","doi":"10.1016/j.isprsjprs.2025.12.002","DOIUrl":"10.1016/j.isprsjprs.2025.12.002","url":null,"abstract":"<div><div>Inverse Synthetic Aperture Radar (ISAR) has been widely applied in remote sensing and space target monitoring. Automatic Target Recognition (ATR) based on ISAR imagery plays a critical role in target interpretation and pose estimation. With the growing adoption of intelligent methods in the ATR domain, the quantity and quality of ISAR data have become decisive factors influencing algorithm performance. However, due to the complexity of ISAR imaging algorithms and the high cost of data acquisition, high-quality ISAR image datasets remain extremely scarce. As a result, learning the underlying characteristics of existing ISAR data to generate large-scale usable samples has become a pressing research focus. Although some preliminary studies have explored ISAR image data augmentation, most of them rely on image sequence interpolation or conditional generation, both of which exhibit critical limitations: the former requires densely sampled image sequences with small angular intervals, while the latter can only model the mapping between limited azimuth conditions and ISAR images. Neither approach is capable of generating images of new targets under unseen azimuth conditions, resulting in poor generalization and leaving substantial room for further exploration. To address these limitations, we formally define a novel research problem, termed ISAR azimuth angle extrapolation. This task fundamentally involves high-dimensional, structured, cross-view image synthesis, requiring the restoration of visual details while ensuring physical consistency and structural stability. To address this problem, we propose ISAR-ExtraNet, a foundation-model-based framework for ISAR azimuth angle extrapolation. ISAR-ExtraNet leverages the strong representation, modeling, and generalization capabilities of pretrained foundation models to generate ISAR images of new targets under novel azimuth conditions. Specifically, the model employs a two-stage coarse-to-fine fine-tuning strategy, incorporating optical image contours and scattering center distribution constraints to guide the generation process. This design enhances both semantic alignment and structural fidelity in the generated ISAR images. Comprehensive experiments demonstrate that ISAR-ExtraNet significantly outperforms baseline methods and fine-tuned foundation models, achieving 28.76 dB in PSNR and 0.80 in SSIM. We hope that the training paradigm introduced in ISAR-ExtraNet will inspire further exploration of the ISAR azimuth extrapolation problem and foster progress in this emerging research area.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"232 ","pages":"Pages 109-123"},"PeriodicalIF":12.2,"publicationDate":"2025-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145684886","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CityVLM: Towards sustainable urban development via multi-view coordinated vision–language model","authors":"Junjue Wang ,&nbsp;Weihao Xuan ,&nbsp;Heli Qi ,&nbsp;Zihang Chen ,&nbsp;Hongruixuan Chen ,&nbsp;Zhuo Zheng ,&nbsp;Junshi Xia ,&nbsp;Yanfei Zhong ,&nbsp;Naoto Yokoya","doi":"10.1016/j.isprsjprs.2025.11.030","DOIUrl":"10.1016/j.isprsjprs.2025.11.030","url":null,"abstract":"<div><div>Vision–language models (VLMs) have shown remarkable promise in Earth Vision, particularly in providing human-interpretable analysis of remote sensing imagery. While existing VLMs excel at general visual perception tasks, they often fall short in addressing the complex needs of geoscience, which requires comprehensive urban analysis across geographical, social, and economic dimensions. To bridge this gap, we expand VLM capabilities to tackle sustainable urban development challenges by integrating two complementary sources: remote sensing (RS) and street-view (SV) imagery. Specifically, we first design a multi-view vision–language dataset (<em>CitySet</em>), comprising 20,589 RS images, 1.1 million SV images, and 0.8 million question–answer pairs. <em>CitySet</em> facilitates geospatial object reasoning, social object analysis, urban economic assessment, and sustainable development report generation. Besides, we develop <em>CityVLM</em> to integrate macro- and micro-level semantics using geospatial and temporal modeling, while its language modeling component generates detailed urban reports. We extensively benchmarked 10 advanced VLMs on our dataset, revealing that state-of-the-art models struggle with urban analysis tasks, primarily due to domain gaps and limited multi-view data alignment capabilities. By addressing these issues, <em>CityVLM</em> achieves superior performance consistently across all tasks and advances automated urban analysis through practical applications like heat island effect monitoring, offering valuable tools for city planners and policymakers in their sustainability efforts.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"232 ","pages":"Pages 62-74"},"PeriodicalIF":12.2,"publicationDate":"2025-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145685023","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"UrbanMMCL: Urban region representations via multi-modal and multi-graph self-supervised contrastive learning","authors":"Jinzhou Cao ,&nbsp;Jiashi Chen ,&nbsp;Xiangxu Wang ,&nbsp;Weiming Huang ,&nbsp;Dongsheng Chen ,&nbsp;Tianhong Zhao ,&nbsp;Wei Tu ,&nbsp;Qingquan Li","doi":"10.1016/j.isprsjprs.2025.11.012","DOIUrl":"10.1016/j.isprsjprs.2025.11.012","url":null,"abstract":"<div><div>Urban region representation learning has emerged as a fundamental approach for diverse urban analytics tasks, where each neighborhood is encoded as a dense embedding vector for effective downstream applications. However, existing approaches suffer from insufficient multi-modal alignment and inadequate spatial relationship modeling, limiting their representation quality and generalizability. To address these challenges, we propose UrbanMMCL, a novel self-supervised framework that integrates multi-modal multi-view contrastive pre-training with unified fine-tuning for comprehensive urban representation learning. UrbanMMCL employs a dual-stage architecture. First, cross-modal contrastive learning aligns diverse data modalities including remote sensing imagery, street view imagery, location encodings, and Vision–Language Model (VLM)-generated textual descriptions. Second, multi-view adaptive graph contrastive learning captures complex spatial relationships across human mobility, functional similarity, and geographic distance perspectives. The framework then fine-tunes all parameters with the learned representations for effective adaptation to downstream tasks. Comprehensive experiments demonstrate that UrbanMMCL consistently outperforms state-of-the-art methods across pollutant emission prediction, population density estimation, and land use classification with minimal fine-tuning requirements, thereby advancing foundation model development for diverse Geo-AI applications.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"232 ","pages":"Pages 75-93"},"PeriodicalIF":12.2,"publicationDate":"2025-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145685024","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mapping oil spills under varying sun glint conditions using a diffusion model with spatial-spectral-frequency constraints","authors":"Kai Du ,&nbsp;Yi Ma ,&nbsp;Zhongwei Li ,&nbsp;Rongjie Liu ,&nbsp;Zongchen Jiang ,&nbsp;Junfang Yang","doi":"10.1016/j.isprsjprs.2025.11.032","DOIUrl":"10.1016/j.isprsjprs.2025.11.032","url":null,"abstract":"<div><div>Marine oil spill detection via optical remote sensing is critically challenged by complex optical signatures induced by sun glint, which causes contrast reversals and masks the spectral features of different oil emulsion types. This study introduces a novel deep learning framework, the Spatial-Spectral Attention Conditioned Diffusion Probabilistic Model with Dual-branch Frequency Parser (OSS-Diff). The core architecture integrates two specialized modules. The first, a physics-informed Dual-branch Frequency Parser (DF-P) module, is designed to disentangle contrast variations by separately processing high-frequency edge features (characteristic of bright spills in strong glint) and low-frequency background information (typical of dark spills in weak glint). Concurrently, a systematically designed Spatial-Spectral Attention (SS-A) module targets spectral ambiguity by adaptively amplifying the discriminative features crucial for identifying oil emulsification states. Extensive experiments confirm the model’s superior performance. Under weak sun glint, it achieved F1-scores of 0.907 for non-emulsified and 0.862 for emulsified slicks. For positive-contrast spills under strong sun glint, it achieved an F1-score of 0.918. Ablation studies validate the synergistic effect of the proposed components, with the full model achieving a 4.9% F1-score gain over the baseline. Significantly, this work also reveals a potential link between the contrast inversion angle and the oil’s refractive index, suggesting a novel avenue for remotely characterizing the physical properties of oil spills. This research provides a robust framework for automated oil spill monitoring, offering a reliable model for environmental protection and emergency response.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"232 ","pages":"Pages 48-61"},"PeriodicalIF":12.2,"publicationDate":"2025-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145657554","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"2Player: A general framework for self-supervised change detection via cooperative learning","authors":"Manon Béchaz ,&nbsp;Emanuele Dalsasso ,&nbsp;Ciprian Tomoiagă ,&nbsp;Marcin Detyniecki ,&nbsp;Devis Tuia","doi":"10.1016/j.isprsjprs.2025.11.024","DOIUrl":"10.1016/j.isprsjprs.2025.11.024","url":null,"abstract":"<div><div>While recent progress in deep learning have improved change detection (CD) in remote sensing, achieving high performance without labeled data remains an open challenge. Current models remain strongly reliant on large-scale annotated datasets, limiting their scalability to new regions and applications. Unsupervised CD methods offer a promising alternative but often suffer from limited representational ability and vulnerability to irrelevant changes in appearance such as seasonal variations. In this work, we propose the 2Player framework, a novel self-supervised method that transforms any existing CD architecture into an unsupervised model by leveraging a cooperation between a change detector and a reconstruction-based model. The two models, or players, guide each other during training: reconstruction errors provide supervision to the change detector, while change predictions guide the reconstruction process. To further improve robustness, we introduce a Geographical Correspondence Module that provides high-frequency structural information, effectively reducing false positives stemming from irrelevant changes in appearance. Furthermore, we propose a simple filtering strategy to mitigate the impact of label noise in CD datasets, contributing in an improved evaluation. We test 2Player on four very high-resolution datasets: HRSCD, for which we improve and release a new, cleaner set of labels, LEVIR-CD, WHU-CD, as well as a new dataset, ValaisCD. Our approach achieves state-of-the-art performance among unsupervised methods on these datasets, and with its architecture-agnostic design, provides a promising direction for bridging the gap between supervised and unsupervised change detection.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"232 ","pages":"Pages 34-47"},"PeriodicalIF":12.2,"publicationDate":"2025-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145657560","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Explainable spatiotemporal deep learning for subseasonal super-resolution forecasting of Arctic sea ice concentration during the melting season","authors":"Jianxin He ,&nbsp;Yuxin Zhao ,&nbsp;Shuo Yang ,&nbsp;Woping Wu ,&nbsp;Jian Wang ,&nbsp;Xiong Deng","doi":"10.1016/j.isprsjprs.2025.11.027","DOIUrl":"10.1016/j.isprsjprs.2025.11.027","url":null,"abstract":"<div><div>Accurate, high-resolution forecasting of Arctic sea-ice concentration (SIC) during the melting season is crucial for climate monitoring and polar navigation, yet remains hindered by the system’s complex, multi-scale, and cross-sphere dynamics. We present MSS-STFormer, an explainable multi-scale spatiotemporal Transformer designed for subseasonal SIC super-resolution forecasting. The model integrates 14 environmental factors spanning the ice, ocean, and atmosphere, and incorporates four specialized modules to enhance spatiotemporal representation and physical consistency. Trained with OSTIA satellite observations and ERA5 reanalysis data, MSS-STFormer achieves high forecasting skill over a 60-day horizon, yielding an RMSE of 0.049, a correlation of 0.9951, an SSIM of 0.9603, and a BACC of 0.9656. Post-hoc explainability methods, Gradient SHAP and LIME—reveal that the model captures a temporally evolving prediction mechanism: early forecasts are dominated by persistence of initial conditions, mid-term phases are governed by atmospheric dynamics such as wind and pressure, and later stages transition to a coupled influence of radiative and dynamic processes. This progression aligns closely with established thermodynamic and dynamic theories of sea-ice evolution, underscoring the model’s ability to identify physically meaningful drivers. The framework demonstrates strong potential for advancing explainable GeoAI in Earth observation, combining predictive accuracy with physical explainability for operational Arctic SIC monitoring and climate applications.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"232 ","pages":"Pages 1-17"},"PeriodicalIF":12.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145625097","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"National mapping of wetland vegetation leaf area index in China using hybrid model with Sentinel-2 and Landsat-8 data","authors":"Jianing Zhen ,&nbsp;Dehua Mao ,&nbsp;Yeqiao Wang ,&nbsp;Junjie Wang ,&nbsp;Chenwei Nie ,&nbsp;Shiqi Huo ,&nbsp;Hengxing Xiang ,&nbsp;Yongxing Ren ,&nbsp;Ling Luo ,&nbsp;Zongming Wang","doi":"10.1016/j.isprsjprs.2025.11.031","DOIUrl":"10.1016/j.isprsjprs.2025.11.031","url":null,"abstract":"<div><div>Leaf area index (LAI) of wetland vegetation provides vital information for its growth condition, structure and functioning. Accurately mapping LAI at a broad scale is essential for conservation and rehabilitation of wetland ecosystem. However, owing to the spatial complexity and periodic inundation characteristics of wetland vegetation, retrieving LAI of wetlands remains a challenging task with significant uncertainty. Here, with 865 in-situ measurements across different wetland biomes in China during 2013–2023, we proposed a hybrid strategy that incorporated active learning (AL) technique, physically-based PROSAIL-5B model, and Random Forest machine learning algorithm to map wetland biomes LAI across China from Sentinel-2 and Landsat-8 imagery. The validation results showed that the hybrid approach outperformed physically-based and empirically-based methods and achieved higher accuracy (R² increased by 0.15–0.40, RMSE decreased by 0.02–0.27, and RRMSE reduced by 3.37–12.78 %). Additionally, three indices that we newly-developed (TBVI5, TBVI3 and TBVI1) exhibited superior potential for LAI inversion across different types of wetland vegetation. Our mapping results exhibited spatial details and consistency, and matched with in-situ observations from Sentinel-2 compared to Landsat-8 and the other MODIS-based products. In this study, we developed the first national-scale mapping of wetland vegetation LAI in China. The findings offer insights into accurate retrieval of LAI in wetland vegetation, providing valuable support for the scientific restoration of wetlands and assessing their responses to climate change.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"232 ","pages":"Pages 18-33"},"PeriodicalIF":12.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145658151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Self-supervised despeckling based solely on SAR intensity images: A general strategy","authors":"Liang Chen ,&nbsp;Yifei Yin ,&nbsp;Hao Shi ,&nbsp;Jingfei He ,&nbsp;Wei Li","doi":"10.1016/j.isprsjprs.2025.11.025","DOIUrl":"10.1016/j.isprsjprs.2025.11.025","url":null,"abstract":"<div><div>Speckle noise is generated along with the SAR imaging mechanism and degrades the quality of SAR images, leading to difficult interpretation. Hence, despeckling is an indispensable step in SAR pre-processing. Fortunately, supervised learning (SL) has proven to be a progressive method for SAR image despeckling. SL methods necessitate the availability of both original SAR images and their speckle-free counterparts during training, whilst speckle-free SAR images do not exist in the real world. Even though there are several substitutes for speckle-free images, the domain gap leads to poor performance and adaptability. Self-supervision provides an approach to training without clean reference. However, most self-supervised methods introduce additional requirements on speckle modeling or specific data, posing challenges in real-world applications. To address these challenges, we propose a general Self-supervised Despeckling Strategy for SAR images (SDS-SAR) that relies solely on speckled intensity data for training. Firstly, the theoretical feasibility of SAR image despeckling without speckle-free images is established. A self-supervised despeckling criteria suitable for diverse SAR images is proposed. Subsequently, a Random-Aware sub-SAMpler with Projection correLation Estimation (RA-SAMPLE) is put forth. Mutually independent training pairs can be derived from actual SAR intensity images. Furthermore, a multi-feature loss function is introduced, consisting of a despeckling term, a regularization term, and a perception term. The performance of speckle suppression and texture preservation is well-balanced. Experiments reveal that the proposed method performs comparably to supervised approaches on synthetic data and outperforms them on actual data. Both visual and quantitative evaluations confirm its superiority over state-of-the-art despeckling techniques. Moreover, the results demonstrates that SDS-SAR provides a novel solution for noise suppression in other multiplicative coherent systems. The trained model and dataset will be available at <span><span>https://github.com/YYF121/SDS-SAR</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"231 ","pages":"Pages 854-873"},"PeriodicalIF":12.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145657555","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}