Two-Step Color-Polarization Demosaicking Network

TL;DR

This paper introduces TCPDNet, a two-step neural network for color-polarization demosaicking that enhances polarization image quality and Stokes parameter accuracy by leveraging a novel reconstruction loss in YCbCr space.

Contribution

The paper proposes a novel two-step neural network architecture for color-polarization demosaicking, incorporating a reconstruction loss in YCbCr space to improve results.

Findings

TCPDNet outperforms existing methods in image quality.

TCPDNet achieves higher accuracy of Stokes parameters.

The YCbCr reconstruction loss improves demosaicking performance.

Abstract

Polarization information of light in a scene is valuable for various image processing and computer vision tasks. A division-of-focal-plane polarimeter is a promising approach to capture the polarization images of different orientations in one shot, while it requires color-polarization demosaicking. In this paper, we propose a two-step color-polarization demosaicking network~(TCPDNet), which consists of two sub-tasks of color demosaicking and polarization demosaicking. We also introduce a reconstruction loss in the YCbCr color space to improve the performance of TCPDNet. Experimental comparisons demonstrate that TCPDNet outperforms existing methods in terms of the image quality of polarization images and the accuracy of Stokes parameters.