Fusion-Decomposition Pan-Sharpening Network With Interactive Learning of Representation Graph

Deep learning (DL)-based pan-sharpening methods have become mainstream due to their exceptional performance. However, the lack of ground truth for supervised learning forces most DL-based methods to use pseudoground truth multispectral images, limiting learning potential and constraining the model&a...

Full description

Saved in:
Bibliographic Details
Main Authors: Yunxuan Tang, Xue Wang, Peng Liu, Tong Li
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10818769/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832590434904309760
author Yunxuan Tang
Xue Wang
Peng Liu
Tong Li
author_facet Yunxuan Tang
Xue Wang
Peng Liu
Tong Li
author_sort Yunxuan Tang
collection DOAJ
description Deep learning (DL)-based pan-sharpening methods have become mainstream due to their exceptional performance. However, the lack of ground truth for supervised learning forces most DL-based methods to use pseudoground truth multispectral images, limiting learning potential and constraining the model's solution space. Unsupervised methods often neglect mutual learning across modalities, leading to insufficient spatial details in pan-sharpened images. To address these issues, this study proposes a fusion-decomposition pan-sharpening model based on interactive learning of representation graphs. This model considers both the compression process from source images to fused results and the decomposition process back to the source images. It aims to leveraging feature consistency between these processes to enhance the spatial and spectral consistency learned by the fusion network in a data-driven manner. Specifically, the fusion network incorporates the meticulously designed representational graph interaction module and the graph interaction fusion module. These modules construct a representational graph structure for cross-modal feature communication, generating a global representation that guides the cross-modal semantic aggregation of multispectral and panchromatic data. In the decomposition network, the spatial structure perception module and the spectral feature extraction module, designed based on the attributes of the source image features, enable the network to better perceive and reconstruct multispectral and panchromatic data from the fused result. This, in turn, enhances the fusion network's perception of spectral information and spatial structure. Qualitative and quantitative results on the IKONOS, GaoFen-2, WorldView-2, and WorldView-3 datasets validate the effectiveness of the proposed method in comparison to other state-of-the-art methods.
format Article
id doaj-art-eddfede2a58749bab8304142f8d1d4ea
institution Kabale University
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-eddfede2a58749bab8304142f8d1d4ea2025-01-24T00:01:00ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01183812382610.1109/JSTARS.2024.352438610818769Fusion-Decomposition Pan-Sharpening Network With Interactive Learning of Representation GraphYunxuan Tang0https://orcid.org/0009-0003-5289-4122Xue Wang1https://orcid.org/0000-0001-6674-8140Peng Liu2https://orcid.org/0000-0002-3283-454XTong Li3https://orcid.org/0000-0002-3257-213XSchool of Information Science and Engineering, Yunnan University, Kunming, ChinaSchool of Information Science and Engineering, Yunnan University, Kunming, ChinaSchool of Information Science and Engineering, Yunnan University, Kunming, ChinaCollege of Big Data, Yunnan Agricultural University, Kunming, ChinaDeep learning (DL)-based pan-sharpening methods have become mainstream due to their exceptional performance. However, the lack of ground truth for supervised learning forces most DL-based methods to use pseudoground truth multispectral images, limiting learning potential and constraining the model's solution space. Unsupervised methods often neglect mutual learning across modalities, leading to insufficient spatial details in pan-sharpened images. To address these issues, this study proposes a fusion-decomposition pan-sharpening model based on interactive learning of representation graphs. This model considers both the compression process from source images to fused results and the decomposition process back to the source images. It aims to leveraging feature consistency between these processes to enhance the spatial and spectral consistency learned by the fusion network in a data-driven manner. Specifically, the fusion network incorporates the meticulously designed representational graph interaction module and the graph interaction fusion module. These modules construct a representational graph structure for cross-modal feature communication, generating a global representation that guides the cross-modal semantic aggregation of multispectral and panchromatic data. In the decomposition network, the spatial structure perception module and the spectral feature extraction module, designed based on the attributes of the source image features, enable the network to better perceive and reconstruct multispectral and panchromatic data from the fused result. This, in turn, enhances the fusion network's perception of spectral information and spatial structure. Qualitative and quantitative results on the IKONOS, GaoFen-2, WorldView-2, and WorldView-3 datasets validate the effectiveness of the proposed method in comparison to other state-of-the-art methods.https://ieeexplore.ieee.org/document/10818769/Deep learning (DL)fusion-decompositiongraph neural network (GNN)pan-sharpening
spellingShingle Yunxuan Tang
Xue Wang
Peng Liu
Tong Li
Fusion-Decomposition Pan-Sharpening Network With Interactive Learning of Representation Graph
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Deep learning (DL)
fusion-decomposition
graph neural network (GNN)
pan-sharpening
title Fusion-Decomposition Pan-Sharpening Network With Interactive Learning of Representation Graph
title_full Fusion-Decomposition Pan-Sharpening Network With Interactive Learning of Representation Graph
title_fullStr Fusion-Decomposition Pan-Sharpening Network With Interactive Learning of Representation Graph
title_full_unstemmed Fusion-Decomposition Pan-Sharpening Network With Interactive Learning of Representation Graph
title_short Fusion-Decomposition Pan-Sharpening Network With Interactive Learning of Representation Graph
title_sort fusion decomposition pan sharpening network with interactive learning of representation graph
topic Deep learning (DL)
fusion-decomposition
graph neural network (GNN)
pan-sharpening
url https://ieeexplore.ieee.org/document/10818769/
work_keys_str_mv AT yunxuantang fusiondecompositionpansharpeningnetworkwithinteractivelearningofrepresentationgraph
AT xuewang fusiondecompositionpansharpeningnetworkwithinteractivelearningofrepresentationgraph
AT pengliu fusiondecompositionpansharpeningnetworkwithinteractivelearningofrepresentationgraph
AT tongli fusiondecompositionpansharpeningnetworkwithinteractivelearningofrepresentationgraph