FPUNet: A Fourier-Enhanced U-Net for Robust 2-D Phase Unwrapping of Noisy InSAR Interferograms
文献类型：期刊论文
| 作者 | He, Yuxiao1,2; Wu, Yuming2; Gao, Xing2 |
| 刊名 | REMOTE SENSING
 |
| 出版日期 | 2026-03-06 |
| 卷号 | 18期号:5页码:808 |
| 关键词 | phase unwrapping (PU) interferometric synthetic aperture radar (InSAR) deep learning Fourier-enhanced U-Net composite loss |
| DOI | 10.3390/rs18050808 |
| 产权排序 | 1 |
| 文献子类 | Article |
| 英文摘要 | Highlights What are the main findings? We propose FPUNet, a Fourier-enhanced phase unwrapping network that integrates frequency-domain global context modeling with multi-scale spatial feature aggregation for robust 2-D unwrapping under steep deformation gradients and multi-source noise. FPUNet improves unwrapping fidelity while preserving physical consistency, as validated by rewrapping checks and closed-loop phase consistency on synthetic and real interferograms. What are the implications of the main findings? The proposed framework provides a practical learning-based alternative to classical unwrapping pipelines for challenging coseismic/complex scenes, with fast inference suitable for large-scale InSAR processing. The physics-informed constraints offer a general strategy to regularize deep unwrapping models, enabling reliable deformation retrieval when the Itoh condition is frequently violated.Highlights What are the main findings? We propose FPUNet, a Fourier-enhanced phase unwrapping network that integrates frequency-domain global context modeling with multi-scale spatial feature aggregation for robust 2-D unwrapping under steep deformation gradients and multi-source noise. FPUNet improves unwrapping fidelity while preserving physical consistency, as validated by rewrapping checks and closed-loop phase consistency on synthetic and real interferograms. What are the implications of the main findings? The proposed framework provides a practical learning-based alternative to classical unwrapping pipelines for challenging coseismic/complex scenes, with fast inference suitable for large-scale InSAR processing. The physics-informed constraints offer a general strategy to regularize deep unwrapping models, enabling reliable deformation retrieval when the Itoh condition is frequently violated.Abstract Two-dimensional phase unwrapping (PU) of interferometric synthetic aperture radar (InSAR) data remains difficult when steep deformation gradients and multi-source disturbances violate the Itoh condition. This study proposes FPUNet, a Fourier-enhanced encoder-decoder for joint denoising and 2-D PU, in which frequency-domain global context modeling is combined with complementary multi-scale spatial aggregation and attention-based feature refinement. Specifically, the bottleneck cascades a Fourier Mixed Residual Block (FMRB), atrous spatial pyramid pooling (ASPP), and a convolutional block attention module (CBAM) to suppress noise while preserving deformation-related fringe structures. FPUNet is trained end-to-end on realistically simulated Sentinel-1 interferograms generated from Shuttle Radar Topography Mission (SRTM) digital elevation models using a physics-informed composite loss that enforces data fidelity, gradient consistency, spectral regularization, and selective rewrapping consistency. On a synthetic benchmark of 1800 test interferograms, FPUNet achieves an RMSE of 0.79 rad, improving over a plain U-Net (1.61 rad) and producing fewer large fringe-number errors than least-squares, SNAPHU, PUNet, and DLPU. Experiments on real Sentinel-1 data over the Datong mining area and the 2022 Menyuan and Luding earthquakes further indicate improved phase closure and rewrapping consistency, particularly in high-gradient coseismic fringes, supporting FPUNet as a robust PU module for InSAR deformation monitoring. |
| URL标识 | 查看原文 |
| WOS关键词 | CONVOLUTIONAL NEURAL-NETWORK ; SENTINEL-1 |
| WOS研究方向 | Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology |
| 语种 | 英语 |
| WOS记录号 | WOS:001713927000001 |
| 出版者 | MDPI |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/221313]  |
| 专题 | 资源与环境信息系统国家重点实验室_外文论文 |
| 通讯作者 | Wu, Yuming |
| 作者单位 | 1.Univ Chinese Acad Sci, Coll Resource & Environm, Beijing 100049, Peoples R China 2.Chinese Acad Sci, State Key Lab Resources & Environm Informat Syst, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China; |
| 推荐引用方式 GB/T 7714 | He, Yuxiao,Wu, Yuming,Gao, Xing. FPUNet: A Fourier-Enhanced U-Net for Robust 2-D Phase Unwrapping of Noisy InSAR Interferograms[J]. REMOTE SENSING,2026,18(5):808. |
| APA | He, Yuxiao,Wu, Yuming,&Gao, Xing.(2026).FPUNet: A Fourier-Enhanced U-Net for Robust 2-D Phase Unwrapping of Noisy InSAR Interferograms.REMOTE SENSING,18(5),808. |
| MLA | He, Yuxiao,et al."FPUNet: A Fourier-Enhanced U-Net for Robust 2-D Phase Unwrapping of Noisy InSAR Interferograms".REMOTE SENSING 18.5(2026):808. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。