UnwrapDiff: Conditional Diffusion for Robust InSAR Phase Unwrapping
This work addresses the reliability of phase unwrapping for geophysical applications like deformation monitoring, representing an incremental improvement over existing methods.
The paper tackled the problem of InSAR phase unwrapping, which is hindered by noise and decorrelation in radar data, by proposing UnwrapDiff, a conditional diffusion model that uses SNAPHU output as guidance, resulting in a 10.11% reduction in NRMSE on average compared to SNAPHU.
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.