Polarization Uncertainty-Guided Diffusion Model for Color Polarization Image Demosaicking

TL;DR

This paper introduces a polarization uncertainty-guided diffusion model for color polarization image demosaicking, improving the reconstruction of polarization features from limited data by leveraging diffusion priors and uncertainty modeling.

Contribution

It proposes a novel diffusion prior approach combined with polarization uncertainty modeling to enhance polarization image reconstruction accuracy.

Findings

Accurately recovers scene polarization characteristics.

Outperforms existing methods in fidelity and visual perception.

Effectively handles limited training data scenarios.

Abstract

Color polarization demosaicking (CPDM) aims to reconstruct full-resolution polarization images of four directions from the color-polarization filter array (CPFA) raw image. Due to the challenge of predicting numerous missing pixels and the scarcity of high-quality training data, existing network-based methods, despite effectively recovering scene intensity information, still exhibit significant errors in reconstructing polarization characteristics (degree of polarization, DOP, and angle of polarization, AOP). To address this problem, we introduce the image diffusion prior from text-to-image (T2I) models to overcome the performance bottleneck of network-based methods, with the additional diffusion prior compensating for limited representational capacity caused by restricted data distribution. To effectively leverage the diffusion prior, we explicitly model the polarization uncertainty during reconstruction and use uncertainty to guide the diffusion model in recovering high error regions. Extensive experiments demonstrate that the proposed method accurately recovers scene polarization characteristics with both high fidelity and strong visual perception.