Abstract

Demosaicking has recently been extensively studied and has achieved significant progress via deep learning. However, all the examples are trained in a supervised manner with the attendance of full-resolution polarization images, which has been compromised for practical applications. In this Letter, we propose to recover full-resolution images from a single mosaic image by combining the deep image prior with the polarization prior to capture the image-specific statistics and further guide the optimization. Specifically, we employ the pixel-wise weight on the intermediate outputs being generated by the recurrent strategy to self-supervise the learning, and the missing pixels can be iteratively and individually recovered. Experimental results on long-wave infrared (LWIR) polarization images demonstrate the effectiveness of the proposed method in terms of both quantitative measurement and visual quality.

© 2022 Optica Publishing Group

Color polarization demosaicking by a convolutional neural network

Yuanyuan Sun, Junchao Zhang, and Rongguang Liang
Opt. Lett. 46(17) 4338-4341 (2021)

Enhanced polarization demosaicking network via a precise angle of polarization loss calculation method

Xiangbo Liu, Xiaobo Li, and Shih-Chi Chen
Opt. Lett. 47(5) 1065-1068 (2022)

Robust photon-efficient imaging using a pixel-wise residual shrinkage network

Gongxin Yao, Yiwei Chen, Yong Liu, Xiaomin Hu, and Yu Pan
Opt. Express 30(11) 18856-18873 (2022)

Polarization image demosaicking using polarization channel difference prior

Rongyuan Wu, Yongqiang Zhao, Ning Li, and Seong G. Kong
Opt. Express 29(14) 22066-22079 (2021)

Line-wise scanning-based super-resolution imaging

Xin Tian, Ying Xiao, Rui Liu, Fang He, and Jiayi Ma
Opt. Lett. 47(9) 2230-2233 (2022)