A Parallel Dual-Task Learning Network for InSAR Phase Retrieval

This work focuses on the problem of InSAR phase retrieval. Current methods consist of two cascaded tasks: phase filtering and phase unwrapping. Unavoidable accumulated errors cause precision loss, and serial computations cause efficiency loss. We propose a parallel dual-task learning work to address these issues for high-quality and efficient InSAR phase retrieval. Methodologically, we retrieve the InSAR phase in a parallel manner instead of a serially cascaded one. Specifically, three core phases throughout the whole processing chain are considered, including feature attraction, task learning, and task balance. First, for feature attraction, considering the InSAR image characteristics, we propose a hybrid Trans-Encoder module to attract features locally and nonlocally. Second, regarding the dual-task needs for feature learning, we propose a dual-decoder to denoise and unwrap parallelly. Third, considering the dual-task's different attributes for task balance, we propose an uncertainty-weighted loss to make balances between tasks. Experiments on both simulated and measured data verify the proposed method's higher precision and efficiency compared to other methods. An ability study is conducted that confirms the effectiveness of the proposed modules.