Exploring Polarimetric Properties Preservation during Reconstruction of PolSAR images using Complex-valued Convolutional Neural Networks

TL;DR

This paper demonstrates that complex-valued neural networks can effectively compress and reconstruct PolSAR data while preserving physical properties, outperforming real-valued models and advancing physics-informed SAR processing.

Contribution

It introduces the use of complex-valued Convolutional AutoEncoders for PolSAR data reconstruction, emphasizing preservation of physical characteristics and advantages over real-valued models.

Findings

Complex-valued networks effectively preserve physical properties.

They outperform real-valued models in reconstruction quality.

The approach enables physics-informed SAR data processing.

Abstract

The inherently complex-valued nature of Polarimetric SAR data necessitates using specialized algorithms capable of directly processing complex-valued representations. However, this aspect remains underexplored in the deep learning community, with many studies opting to convert complex signals into the real domain before applying conventional real-valued models. In this work, we leverage complex-valued neural networks and investigate the performance of complex-valued Convolutional AutoEncoders. We show that these networks can effectively compress and reconstruct fully polarimetric SAR data while preserving essential physical characteristics, as demonstrated through Pauli, Krogager, and Cameron coherent decompositions, as well as the non-coherent $H-\alpha$ decomposition. Finally, we highlight the advantages of complex-valued neural networks over their real-valued counterparts. These insights pave the way for developing robust, physics-informed, complex-valued generative models for SAR data processing.