A Dual-Channel Deep Learning Method for Demosaicing Based on an Optimized Color-Polarization Array
- 18 August 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (19) , 36407-36422
Abstract
Polarization and color are two essential attributes of color-polarization imaging In recent years, the application of both polarization and color information has gained widespread attention across various image processing research domains. This paper proposes a novel color-polarization array design method by employing the non-dominated sorting genetic algorithm (NSGA-II) to generate mosaicked images with color and polarization information, followed by a dual-channel guided deep-learning reconstruction network to recover these attributes. This optimization method produces a compact 3×3 array with an innovative filter layout. This minimizes polarization angles and unit array size while maintaining the integrity of color-polarization information in the reconstructed images. In addition, the use of deep learning modules enables a more thorough restoration of missing information in mosaicked images from a new perspective. Experimental results demonstrate that our network can accurately demosaic the mosaicked output of the proposed array, effectively recovering both the color and the polarization data. Our compact 3×3 array outperforms the classical 4×4 polar-bayer array on benchmark color-polarization image datasets.Additionally, the reconstruction algorithm preserves the fidelity of color and polarization after demosaicing.Keywords
Funding Information
- Equipment Pre-research Ordnance Industry Applied Innovation Project (627010103)
- National Natural Science Foundation of China (52472439)
This publication has 61 references indexed in Scilit:
- Polarization image demosaicking based on homogeneity spaceOptics and Lasers in Engineering, 2024
- Demystifying Deep Learning2023
- Illumination-invariant road detection and tracking using LWIR polarization characteristicsISPRS Journal of Photogrammetry and Remote Sensing, 2021
- Investigation of achromatic micro polarizer array for polarization imaging in visible-infrared bandOptik, 2018
- Edge-aware smoothing through adaptive interpolationSignal, Image and Video Processing, 2017
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Practical implementation of LMMSE demosaicing using luminance and chrominance spacesComputer Vision and Image Understanding, 2007
- Multiresponse robust design: Mean square error (MSE) criterionApplied Mathematics and Computation, 2006
- Color processing in digital camerasIEEE Micro, 1998
- Functional similarities between polarization vision and color visionVision Research, 1977