UnwrapDiff: A Conditional Diffusion Model for InSAR Phase Unwrapping
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914257822547968 |
|---|---|
| author | Song, Yijia Biggs, Juliet Achim, Alin Popescu, Robert Orrego, Simon Anantrasirichai, Nantheera |
| author_facet | Song, Yijia Biggs, Juliet Achim, Alin Popescu, Robert Orrego, Simon Anantrasirichai, Nantheera |
| contents | Phase unwrapping is a fundamental problem in InSAR data processing, supporting geophysical applications such as deformation monitoring and hazard assessment. Its reliability is limited by noise and decorrelation in radar acquisitions, which makes accurate reconstruction of the deformation signal challenging. We propose a denoising diffusion probabilistic model (DDPM)-based framework for InSAR phase unwrapping, UnwrapDiff, in which the output of the traditional minimum cost flow algorithm (SNAPHU) is incorporated as conditional guidance. To evaluate robustness, we construct a synthetic dataset that incorporates atmospheric effects and diverse noise patterns, representative of realistic InSAR observations. Experiments show that the proposed model leverages the conditional prior while reducing the effect of diverse noise patterns, achieving on average a 10.11\% reduction in NRMSE compared to SNAPHU. It also achieves better reconstruction quality in difficult cases such as dyke intrusions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_04749 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | UnwrapDiff: A Conditional Diffusion Model for InSAR Phase Unwrapping Song, Yijia Biggs, Juliet Achim, Alin Popescu, Robert Orrego, Simon Anantrasirichai, Nantheera Geophysics Artificial Intelligence Phase unwrapping is a fundamental problem in InSAR data processing, supporting geophysical applications such as deformation monitoring and hazard assessment. Its reliability is limited by noise and decorrelation in radar acquisitions, which makes accurate reconstruction of the deformation signal challenging. We propose a denoising diffusion probabilistic model (DDPM)-based framework for InSAR phase unwrapping, UnwrapDiff, in which the output of the traditional minimum cost flow algorithm (SNAPHU) is incorporated as conditional guidance. To evaluate robustness, we construct a synthetic dataset that incorporates atmospheric effects and diverse noise patterns, representative of realistic InSAR observations. Experiments show that the proposed model leverages the conditional prior while reducing the effect of diverse noise patterns, achieving on average a 10.11\% reduction in NRMSE compared to SNAPHU. It also achieves better reconstruction quality in difficult cases such as dyke intrusions. |
| title | UnwrapDiff: A Conditional Diffusion Model for InSAR Phase Unwrapping |
| topic | Geophysics Artificial Intelligence |
| url | https://arxiv.org/abs/2512.04749 |