Architectural Unification for Polarimetric Imaging Across Multiple Degradations

2026-03-06

AI Summary

This work addresses the challenge of accurately recovering physically consistent polarization parameters—such as total intensity, degree of polarization, and angle of polarization—from real-world polarimetric imaging, which is often degraded by low-light noise, motion blur, and mosaic artifacts. The authors propose the first unified neural network architecture that jointly models the image and Stokes domains within a single-stage, end-to-end trainable framework, incorporating explicit physical consistency constraints. By sharing a common structure across diverse degradation types and avoiding task-specific designs or multi-stage pipelines, the method mitigates error accumulation and enhances generalization. Experimental results demonstrate state-of-the-art performance in low-light denoising, motion deblurring, and demosaicking tasks, significantly improving both physical fidelity and robustness across varying imaging conditions.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Polarimetric imaging aims to recover polarimetric parameters, including Total Intensity (TI), Degree of Polarization (DoP), and Angle of Polarization (AoP), from captured polarized measurements. In real-world scenarios, these measurements are frequently affected by diverse degradations such as low-light noise, motion blur, and mosaicing artifacts. Due to the nonlinear dependency of DoP and AoP on the measured intensities, accurately retrieving physically consistent polarimetric parameters from degraded observations remains highly challenging. Existing approaches typically adopt task-specific network architectures tailored to individual degradation types, limiting their adaptability across different restoration scenarios. Moreover, many methods rely on multi-stage processing pipelines that suffer from error accumulation, or operate solely in a single domain (either image or Stokes domain), failing to fully exploit the intrinsic physical relationships between them. In this work, we propose a unified architectural framework for polarimetric imaging that is structurally shared across multiple degradation scenarios. Rather than redesigning network structures for each task, our framework maintains a consistent architectural design while being trained separately for different degradations. The model performs single-stage joint image-Stokes processing, avoiding error accumulation and explicitly preserving physical consistency. Extensive experiments show that this unified architectural design, when trained for specific degradation types, consistently achieves state-of-the-art performance across low-light denoising, motion deblurring, and demosaicing tasks, establishing a versatile and physically grounded solution for degraded polarimetric imaging.

Problem

• Polarimetric imaging
• Image degradation
• Physical consistency
• DoP
• AoP

Innovation

• Architectural Unification
• Polarimetric Imaging
• Joint Image-Stokes Processing
• Physical Consistency
• Multi-degradation Restoration