A Novel Model for Interferometric Phase Reconstruction Based on Multi-Stage Conditional GANs

Reconstructing the interferometric phase in decorrelated regions is a significant challenge in interferometric synthetic aperture radar (InSAR) techniques, as decorrelation disrupts the continuity of phase fringes and obscures critical information. This paper presents a novel two-stage generative ad...

Full description

Saved in:
Bibliographic Details
Main Authors: M. Abdallah, X. Ding, S. Wu
Format: Article
Language:English
Published: Copernicus Publications 2025-07-01
Series:ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://isprs-annals.copernicus.org/articles/X-G-2025/11/2025/isprs-annals-X-G-2025-11-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849428284126789632
author M. Abdallah
M. Abdallah
M. Abdallah
X. Ding
X. Ding
S. Wu
S. Wu
author_facet M. Abdallah
M. Abdallah
M. Abdallah
X. Ding
X. Ding
S. Wu
S. Wu
author_sort M. Abdallah
collection DOAJ
description Reconstructing the interferometric phase in decorrelated regions is a significant challenge in interferometric synthetic aperture radar (InSAR) techniques, as decorrelation disrupts the continuity of phase fringes and obscures critical information. This paper presents a novel two-stage generative adversarial network (GAN) framework to address this issue. In the first stage, GAN is designed to reconnect fragmented phase fringes. In the second stage, GAN focuses on reconstructing the phase in masked regions guided by the reconnected fringes achieved from the first stage. The proposed model was trained on a simulated topographic phase with the SRTAM product. The proposed model achieves a structural similarity index (SSIM) of 0.9 and a peak signal-to-noise ratio (PSNR) of 30.4. Then, we conducted a quantitative evaluation with a real interferogram from the Greater Bay Area (GBA). The experiment results demonstrated the generalization capabilities of the proposal model, with an average correlation of 0.8 between the predicted and actual phases. The proposed approach can effectively preserve phase continuity, reconstruct masked areas, and mitigate the impact of decorrelation. It shows potential for use in topographic retrieval and ground deformation monitoring in InSAR applications.
format Article
id doaj-art-465fe4cc58d24afe86e187ea2921e957
institution Kabale University
issn 2194-9042
2194-9050
language English
publishDate 2025-07-01
publisher Copernicus Publications
record_format Article
series ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj-art-465fe4cc58d24afe86e187ea2921e9572025-08-20T03:28:44ZengCopernicus PublicationsISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences2194-90422194-90502025-07-01X-G-2025111710.5194/isprs-annals-X-G-2025-11-2025A Novel Model for Interferometric Phase Reconstruction Based on Multi-Stage Conditional GANsM. Abdallah0M. Abdallah1M. Abdallah2X. Ding3X. Ding4S. Wu5S. Wu6Department of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, Hong Kong, ChinaResearch Institution for Land and Space, The Hong Kong Polytechnic University, Hong Kong, ChinaPublic Works Department, Mansoura University, Mansoura, EgyptDepartment of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, Hong Kong, ChinaResearch Institution for Land and Space, The Hong Kong Polytechnic University, Hong Kong, ChinaDepartment of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, Hong Kong, ChinaResearch Institution for Land and Space, The Hong Kong Polytechnic University, Hong Kong, ChinaReconstructing the interferometric phase in decorrelated regions is a significant challenge in interferometric synthetic aperture radar (InSAR) techniques, as decorrelation disrupts the continuity of phase fringes and obscures critical information. This paper presents a novel two-stage generative adversarial network (GAN) framework to address this issue. In the first stage, GAN is designed to reconnect fragmented phase fringes. In the second stage, GAN focuses on reconstructing the phase in masked regions guided by the reconnected fringes achieved from the first stage. The proposed model was trained on a simulated topographic phase with the SRTAM product. The proposed model achieves a structural similarity index (SSIM) of 0.9 and a peak signal-to-noise ratio (PSNR) of 30.4. Then, we conducted a quantitative evaluation with a real interferogram from the Greater Bay Area (GBA). The experiment results demonstrated the generalization capabilities of the proposal model, with an average correlation of 0.8 between the predicted and actual phases. The proposed approach can effectively preserve phase continuity, reconstruct masked areas, and mitigate the impact of decorrelation. It shows potential for use in topographic retrieval and ground deformation monitoring in InSAR applications.https://isprs-annals.copernicus.org/articles/X-G-2025/11/2025/isprs-annals-X-G-2025-11-2025.pdf
spellingShingle M. Abdallah
M. Abdallah
M. Abdallah
X. Ding
X. Ding
S. Wu
S. Wu
A Novel Model for Interferometric Phase Reconstruction Based on Multi-Stage Conditional GANs
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title A Novel Model for Interferometric Phase Reconstruction Based on Multi-Stage Conditional GANs
title_full A Novel Model for Interferometric Phase Reconstruction Based on Multi-Stage Conditional GANs
title_fullStr A Novel Model for Interferometric Phase Reconstruction Based on Multi-Stage Conditional GANs
title_full_unstemmed A Novel Model for Interferometric Phase Reconstruction Based on Multi-Stage Conditional GANs
title_short A Novel Model for Interferometric Phase Reconstruction Based on Multi-Stage Conditional GANs
title_sort novel model for interferometric phase reconstruction based on multi stage conditional gans
url https://isprs-annals.copernicus.org/articles/X-G-2025/11/2025/isprs-annals-X-G-2025-11-2025.pdf
work_keys_str_mv AT mabdallah anovelmodelforinterferometricphasereconstructionbasedonmultistageconditionalgans
AT mabdallah anovelmodelforinterferometricphasereconstructionbasedonmultistageconditionalgans
AT mabdallah anovelmodelforinterferometricphasereconstructionbasedonmultistageconditionalgans
AT xding anovelmodelforinterferometricphasereconstructionbasedonmultistageconditionalgans
AT xding anovelmodelforinterferometricphasereconstructionbasedonmultistageconditionalgans
AT swu anovelmodelforinterferometricphasereconstructionbasedonmultistageconditionalgans
AT swu anovelmodelforinterferometricphasereconstructionbasedonmultistageconditionalgans
AT mabdallah novelmodelforinterferometricphasereconstructionbasedonmultistageconditionalgans
AT mabdallah novelmodelforinterferometricphasereconstructionbasedonmultistageconditionalgans
AT mabdallah novelmodelforinterferometricphasereconstructionbasedonmultistageconditionalgans
AT xding novelmodelforinterferometricphasereconstructionbasedonmultistageconditionalgans
AT xding novelmodelforinterferometricphasereconstructionbasedonmultistageconditionalgans
AT swu novelmodelforinterferometricphasereconstructionbasedonmultistageconditionalgans
AT swu novelmodelforinterferometricphasereconstructionbasedonmultistageconditionalgans