{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T18:10:18Z","timestamp":1774030218385,"version":"3.50.1"},"reference-count":54,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T00:00:00Z","timestamp":1737072000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Comput. Sci."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Pansharpening is an important remote sensing task that aims to produce high-resolution multispectral (MS) images by combining low-resolution MS images with high-resolution panchromatic (PAN) images. Although deep learning-based pansharpening has shown impressive results, the majority of these models frequently struggle to balance spatial and spectral information, resulting in artifacts and a loss of detail in pansharpened images. Furthermore, these models may fail to properly integrate spatial and spectral information, leading to poor performance in complex scenarios. Additionally, these models face challenges such as gradient vanishing and overfitting.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>This paper proposes a dual-path and multi-scale pansharpening network (DMPNet). It consists of three modules: the feature extraction module (FEM), the multi-scale adaptive attention fusion module (MSAAF), and the image reconstruction module (IRM). The FEM is designed with two paths, namely the primary and secondary paths. The primary path captures global spatial and spectral information using dilated convolutions, while the secondary path focuses on fine-grained details using shallow convolutions and attention-guided feature extraction. The MSAAF module adaptively combines spatial and spectral data across different scales, employing a self-calibrated attention (SCA) mechanism for dynamic weighting of local and global contexts and a spectral alignment network (SAN) to ensure spectral consistency. Finally, to achieve optimal spatial and spectral reconstruction, the IRM decomposes the fused features into low- and high-frequency components using discrete wavelet transform (DWT).<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The proposed DMPNet outperforms competitive models in terms of ERGAS, SCC (WR), SCC (NR), PSNR, Q, QNR, and JQM by approximately 1.24%, 1.18%, 1.37%, 1.42%, 1.26%, 1.31%, and 1.23%, respectively.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>Extensive experimental results and evaluations reveal that the DMPNet is more efficient and robust than competing pansharpening models.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fcomp.2024.1455963","type":"journal-article","created":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T06:53:17Z","timestamp":1737096797000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["DMPNet: dual-path and multi-scale pansharpening network"],"prefix":"10.3389","volume":"6","author":[{"given":"Gurpreet","family":"Kaur","sequence":"first","affiliation":[]},{"given":"Manisha","family":"Malhotra","sequence":"additional","affiliation":[]},{"given":"Dilbag","family":"Singh","sequence":"additional","affiliation":[]},{"given":"Sunita","family":"Singhal","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2025,1,17]]},"reference":[{"key":"B1","doi-asserted-by":"crossref","first-page":"645","DOI":"10.1007\/978-3-319-25468-5_14","article-title":"\u201cDiscrete wavelet transform (DWT),\u201d","author":"Alessio","year":"2016","journal-title":"Digital Signal Processing and Spectral Analysis for Scientists: Concepts and Applications"},{"key":"B2","doi-asserted-by":"publisher","first-page":"193","DOI":"10.14358\/PERS.74.2.193","article-title":"Multispectral and panchromatic data fusion assessment without reference","volume":"74","author":"Alparone","year":"2008","journal-title":"Photogramm. Eng. Remote Sens"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1687-6180-2011-79","article-title":"A survey of classical methods and new trends in pansharpening of multispectral images","volume":"2011","author":"Amro","year":"2011","journal-title":"EURASIP J Adv Signal Proc"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1109\/JSYST.2016.2565900","article-title":"Multisensor satellite image fusion and networking for all-weather environmental monitoring","volume":"12","author":"Chang","year":"2016","journal-title":"IEEE Syst. J"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3299356","article-title":"Unsupervised deep learning-based pansharpening with jointly-enhanced spectral and spatial fidelity","author":"Ciotola","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens"},{"key":"B6","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1109\/MGRS.2022.3187652","article-title":"Machine learning in pansharpening: a benchmark, from shallow to deep networks","volume":"10","author":"Deng","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Magaz"},{"key":"B7","doi-asserted-by":"crossref","first-page":"3141","DOI":"10.1109\/IGARSS.2019.8897928","article-title":"\u201cSSCNET: spectral-spatial consistency optimization of CNN for pansharpening,\u201d","volume-title":"IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium","author":"Doi","year":"2019"},{"key":"B8","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/j.compmedimag.2018.09.004","article-title":"SD-CNN: a shallow-deep cnn for improved breast cancer diagnosis","volume":"70","author":"Gao","year":"2018","journal-title":"Comp. Med. Imag. Graph"},{"key":"B9","doi-asserted-by":"publisher","first-page":"616","DOI":"10.3390\/rs16040616","article-title":"GSA-SIAMNET: a siamese network with gradient-based spatial attention for pan-sharpening of multi-spectral images","volume":"16","author":"Gao","year":"2024","journal-title":"Remote Sens"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2021.3060958","article-title":"Generative adversarial network for pansharpening with spectral and spatial discriminators","volume":"60","author":"Gastineau","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens"},{"key":"B11","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1080\/2150704X.2018.1547443","article-title":"A novel iterative pca-based pansharpening method","volume":"10","author":"Ghadjati","year":"2019","journal-title":"Remote Sens. Lett"},{"key":"B12","doi-asserted-by":"publisher","first-page":"2194","DOI":"10.1109\/TGRS.2015.2497309","article-title":"A compressed-sensing-based pan-sharpening method for spectral distortion reduction","volume":"54","author":"Ghahremani","year":"2015","journal-title":"IEEE Trans. Geosci. Remote Sens"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1188","DOI":"10.1109\/JSTARS.2019.2898574","article-title":"Pansharpening via detail injection based convolutional neural networks","volume":"12","author":"He","year":"2019","journal-title":"IEEE J. Select. Topics Appl. Earth Observat. Remote Sens"},{"key":"B14","doi-asserted-by":"publisher","first-page":"113856","DOI":"10.1016\/j.rse.2023.113856","article-title":"Cross-city matters: A multimodal remote sensing benchmark dataset for cross-city semantic segmentation using high-resolution domain adaptation networks","volume":"299","author":"Hong","year":"2023","journal-title":"Remote Sens. Environm"},{"key":"B15","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1016\/j.neucom.2022.07.071","article-title":"Multi-level features fusion via cross-layer guided attention for hyperspectral pansharpening","volume":"506","author":"Hou","year":"2022","journal-title":"Neurocomputing"},{"key":"B16","first-page":"7132","article-title":"\u201cSqueeze-and-excitation networks,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Hu","year":"2018"},{"key":"B17","doi-asserted-by":"publisher","first-page":"111935","DOI":"10.1016\/j.measurement.2022.111935","article-title":"Multi-scale convolutional network with channel attention mechanism for rolling bearing fault diagnosis","volume":"203","author":"Huang","year":"2022","journal-title":"Measurement"},{"key":"B18","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1109\/JAS.2023.123987","article-title":"Paps: Progressive attention-based pan-sharpening","volume":"11","author":"Jia","year":"2024","journal-title":"IEEE-CAA J. Automat. Sinica"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1666","DOI":"10.3390\/rs15061666","article-title":"Multi-scale and multi-stream fusion network for pansharpening","volume":"15","author":"Jian","year":"2023","journal-title":"Remote Sens"},{"key":"B20","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1016\/j.inffus.2021.09.002","article-title":"Laplacian pyramid networks: a new approach for multispectral pansharpening","volume":"78","author":"Jin","year":"2022","journal-title":"Inform. Fusion"},{"key":"B21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ICSIDP47821.2019.9173129","article-title":"\u201cPan-sharpening framework based on laplacian sharpening with brovey,\u201d","volume-title":"2019 IEEE International Conference on Signal, Information and Data Processing (ICSIDP)","author":"Khan","year":"2019"},{"key":"B22","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1007\/s42452-019-1903-4","article-title":"Shallow convolutional neural network for image classification","volume":"2","author":"Lei","year":"2020","journal-title":"SN Appl. Sci"},{"key":"B23","doi-asserted-by":"publisher","first-page":"985","DOI":"10.1109\/LGRS.2013.2284282","article-title":"An improved adaptive intensity-hue-saturation method for the fusion of remote sensing images","volume":"11","author":"Leung","year":"2013","journal-title":"IEEE Geosci. Remote Sens. Lett"},{"key":"B24","doi-asserted-by":"publisher","first-page":"102408","DOI":"10.1016\/j.inffus.2024.102408","article-title":"CasFormer: Cascaded transformers for fusion-aware computational hyperspectral imaging","volume":"108","author":"Li","year":"2024","journal-title":"Inform. Fusion"},{"key":"B25","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/j.isprsjprs.2022.04.001","article-title":"Hypernet: a deep network for hyperspectral, multispectral, and panchromatic image fusion","volume":"188","author":"Li","year":"2022","journal-title":"ISPRS J. Photogrammet. Remote Sens"},{"key":"B26","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1504\/IJCSE.2024.137282","article-title":"Pyramid hierarchical network for multispectral pan-sharpening","volume":"27","author":"Li","year":"2024","journal-title":"Int. J. Comp. Sci. Eng"},{"key":"B27","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1109\/JSTARS.2023.3332459","article-title":"Transformer-based dual-branch multiscale fusion network for pan-sharpening remote sensing images","volume":"17","author":"Li","year":"2023","journal-title":"IEEE J. Select. Topics in Appl. Earth Observat. Remote Sens"},{"key":"B28","doi-asserted-by":"publisher","first-page":"23973","DOI":"10.1007\/s00521-023-08872-8","article-title":"SCAU-Net: 3D self-calibrated attention U-Net for brain tumor segmentation","volume":"35","author":"Liu","year":"2023","journal-title":"Neural Comp. Appl"},{"key":"B29","doi-asserted-by":"publisher","first-page":"3340193","DOI":"10.1109\/TGRS.2023.3340193","article-title":"Rethinking pan-sharpening via spectral-band modulation","volume":"62","author":"Liu","year":"2024","journal-title":"IEEE trans. Geosci. Remote sens"},{"key":"B30","doi-asserted-by":"publisher","first-page":"18021","DOI":"10.1109\/JSEN.2022.3195243","article-title":"Multimodal sensors image fusion for higher resolution remote sensing pan sharpening","volume":"22","author":"Liu","year":"2022","journal-title":"IEEE Sensors J"},{"key":"B31","doi-asserted-by":"crossref","first-page":"619","DOI":"10.1145\/3178876.3186128","article-title":"\u201cLow rank spectral network alignment,\u201d","author":"Nassar","year":"2018","journal-title":"Proceedings of the 2018 World Wide Web Conference"},{"key":"B32","doi-asserted-by":"publisher","first-page":"9292","DOI":"10.3390\/rs70709292","article-title":"Joint quality measure for evaluation of pansharpening accuracy","volume":"7","author":"Palubinskas","year":"2015","journal-title":"Remote Sens"},{"key":"B33","doi-asserted-by":"publisher","first-page":"2898","DOI":"10.1080\/01431161.2020.1864056","article-title":"A pansharpening scheme using spectral graph wavelet transforms and convolutional neural networks","volume":"42","author":"Saxena","year":"2021","journal-title":"Int. J. Remote Sens"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3422896","article-title":"Unsupervised pan-sharpening network incorporating imaging spectral prior and spatial-spectral compensation","author":"Shen","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens"},{"key":"B35","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.neucom.2022.11.068","article-title":"Domain-specific knowledge-driven pan-sharpening algorithm","volume":"520","author":"Shi","year":"2023","journal-title":"Neurocomputing"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2022.3152425","article-title":"Transformer-based regression network for pansharpening remote sensing images","volume":"60","author":"Su","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens"},{"key":"B37","volume-title":"Data Fusion: Definitions and Architectures\u2014Fusion of Images of Different Spatial Resolutions","author":"Wald","year":"2002"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3454124","article-title":"A deep error removal network for pan-sharpening","author":"Wang","year":"","journal-title":"IEEE Geosci. Remote Sens. Lett"},{"key":"B39","doi-asserted-by":"publisher","first-page":"110247","DOI":"10.1016\/j.patcog.2023.110247","article-title":"Pan-sharpening via intrinsic decomposition knowledge distillation","volume":"149","author":"Wang","year":"","journal-title":"Pattern Recognit"},{"key":"B40","doi-asserted-by":"publisher","first-page":"19945","DOI":"10.1007\/s11042-019-7377-y","article-title":"Multi-scale dilated convolution of convolutional neural network for image denoising","volume":"78","author":"Wang","year":"2019","journal-title":"Multimedia Tools Appl"},{"key":"B41","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1109\/97.995823","article-title":"A universal image quality index","volume":"9","author":"Wang","year":"2002","journal-title":"IEEE Signal Process. Lett"},{"key":"B42","doi-asserted-by":"crossref","first-page":"5495","DOI":"10.1145\/3581783.3612016","article-title":"\u201cHyperspectral image denoising with spectrum alignment,\u201d","author":"Xiao","year":"2023","journal-title":"Proceedings of the 31st ACM International Conference on Multimedia"},{"key":"B43","doi-asserted-by":"publisher","first-page":"3170376","DOI":"10.1109\/LGRS.2022.3170376","article-title":"Progressive pan-sharpening via cross-scale collaboration networks","volume":"19","author":"Yang","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett"},{"key":"B44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.inffus.2021.10.001","article-title":"A theoretical and practical survey of image fusion methods for multispectral pansharpening","volume":"79","author":"Yilmaz","year":"2022","journal-title":"Inform. Fusion"},{"key":"B45","doi-asserted-by":"publisher","first-page":"1736","DOI":"10.3390\/rs14071736","article-title":"Multiscale spatial-spectral interaction transformer for pan-sharpening","volume":"14","author":"Zhang","year":"2022","journal-title":"Remote Sens"},{"key":"B46","doi-asserted-by":"publisher","first-page":"61530","DOI":"10.1109\/ACCESS.2022.3182104","article-title":"Attention-guided feature extraction and multiscale feature fusion 3D resnet for automated pulmonary nodule detection","volume":"10","author":"Zhang","year":"2022","journal-title":"IEEE Access"},{"key":"B47","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1016\/j.inffus.2022.12.026","article-title":"Panchromatic and multispectral image fusion for remote sensing and earth observation: concepts, taxonomy, literature review, evaluation methodologies and challenges ahead","volume":"93","author":"Zhang","year":"2023","journal-title":"Inform. Fusion"},{"key":"B48","doi-asserted-by":"publisher","first-page":"2318","DOI":"10.3390\/rs12142318","article-title":"Perceppan: towards unsupervised pan-sharpening based on perceptual loss","volume":"12","author":"Zhou","year":"2020","journal-title":"Remote Sens"},{"key":"B49","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1080\/014311698215973","article-title":"A wavelet transform method to merge landsat tm and spot panchromatic data","volume":"19","author":"Zhou","year":"1998","journal-title":"Int. J. Remote Sens"},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3279931","article-title":"Rethinking pan-sharpening in closed-loop regularization","author":"Zhou","year":"","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B51","doi-asserted-by":"crossref","DOI":"10.1145\/3503161.3547774","article-title":"\u201cNormalization-based feature selection and restitution for pan-sharpening,\u201d","volume-title":"30th ACM International Conference on Multimedia (MM)","author":"Zhou","year":""},{"key":"B52","article-title":"\u201cSpatial-frequency domain information integration for pan-sharpening,\u201d","author":"Zhou","year":"","journal-title":"17th European Conference on Computer Vision (ECCV)"},{"key":"B53","doi-asserted-by":"publisher","first-page":"3232384","DOI":"10.1109\/TGRS.2022.3232384","article-title":"Modality-aware feature integration for pan-sharpening","volume":"61","author":"Zhou","year":"","journal-title":"IEEE Trans. Geosci. Remote Sens"},{"key":"B54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3475485","article-title":"Probing synergistic high-order interaction for multi-modal image fusion","author":"Zhou","year":"2024","journal-title":"IEEE Trans. Pattern Analy. Mach. Intellig"}],"container-title":["Frontiers in Computer Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcomp.2024.1455963\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T06:53:22Z","timestamp":1737096802000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcomp.2024.1455963\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,17]]},"references-count":54,"alternative-id":["10.3389\/fcomp.2024.1455963"],"URL":"https:\/\/doi.org\/10.3389\/fcomp.2024.1455963","relation":{},"ISSN":["2624-9898"],"issn-type":[{"value":"2624-9898","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,17]]},"article-number":"1455963"}}