PFNet: an unsupervised deep network for polarization image fusion

Abstract

Image fusion is the key step to improve the performance of object detection in polarization images. We propose an unsupervised deep network to address the polarization image fusion issue. The network learns end-to-end mapping for fused images from intensity and degree of linear polarization images, without the ground truth of fused images. Customized architecture and loss function are designed to boost performance. Experimental results show that our proposed network outperforms other state-of-the-art methods in terms of visual quality and quantitative measurement.

© 2020 Optical Society of America

Deep-learning-based hyperspectral recovery from a single RGB image

Junchao Zhang, Yuanyuan Sun, Jianlai Chen, Degui Yang, and Rongguang Liang
Opt. Lett. 45(20) 5676-5679 (2020)

Learning a convolutional demosaicing network for microgrid polarimeter imagery

Junchao Zhang, Jianbo Shao, Haibo Luo, Xiangyue Zhang, Bin Hui, Zheng Chang, and Rongguang Liang
Opt. Lett. 43(18) 4534-4537 (2018)

IPLNet: a neural network for intensity-polarization imaging in low light

Haofeng Hu, Yang Lin, Xiaobo Li, Pengfei Qi, and Tiegen Liu
Opt. Lett. 45(22) 6162-6165 (2020)

Multi-focus image fusion method using energy of Laplacian and a deep neural network

Hao Zhai and Yi Zhuang
Appl. Opt. 59(6) 1684-1694 (2020)

Virtual brightfield and fluorescence staining for Fourier ptychography via unsupervised deep learning

Ruihai Wang, Pengming Song, Shaowei Jiang, Chenggang Yan, Jiakai Zhu, Chengfei Guo, Zichao Bian, Tianbo Wang, and Guoan Zheng
Opt. Lett. 45(19) 5405-5408 (2020)