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

2026-02-06

AI Summary

This work proposes a complex-valued convolutional autoencoder that directly processes fully polarimetric synthetic aperture radar (PolSAR) data in the complex domain, circumventing the common practice of converting such data to real-valued representations which often compromises inherent polarimetric physical properties. The study presents the first systematic evaluation of complex-valued neural networks in preserving both coherent (Pauli, Krogager, Cameron) and incoherent (H-α) decomposition characteristics during data compression and reconstruction. Experimental results demonstrate that the proposed method significantly outperforms real-valued counterparts, achieving high-fidelity reconstruction while effectively maintaining the underlying polarimetric scattering mechanisms. These findings underscore the advantages of complex-valued architectures in ensuring physical consistency for PolSAR data modeling.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Machine Learning: Deep Generative Models & Autoencoders
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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.

Problem

• PolSAR
• polarimetric preservation
• complex-valued neural networks
• image reconstruction
• deep learning

Innovation

• Complex-valued Neural Networks
• PolSAR Image Reconstruction
• Polarimetric Properties Preservation
• Convolutional AutoEncoder
• Physics-informed Deep Learning