Abstract

The fusion of infrared intensity and polarization images can generate a single image with better visible perception and more vital information. Existing fusion methods based on a convolutional neural network (CNN), with local feature extraction, have the limitation of fully exploiting salient target features of polarization. In this Letter, we propose a transformer-based deep network to improve the performance of infrared polarization image fusion. Compared with existing CNN-based methods, our model can encode long-range features of infrared polarization images to obtain global contextual information using the self-attention mechanism. We also design a loss function with the self-supervised constraint to boost the performance of fusion. Experiments on the public infrared polarization dataset validate the effectiveness of the proposed method. Our approach achieves better fusion performance than the state-of-the-art.

© 2022 Optica Publishing Group

DBPFNet: a dual-band polarization image fusion network based on the attention mechanism and atrous spatial pyramid pooling

Yunan Wu, Jun Chang, Ning Ma, Yining Yang, Zhongye Ji, and Yi Huang
Opt. Lett. 48(19) 5125-5128 (2023)

Noise-aware infrared polarization image fusion based on salient prior with attention-guided filtering network

Kunyuan Li, Meibin Qi, Shuo Zhuang, Yimin Liu, and Jun Gao
Opt. Express 31(16) 25781-25796 (2023)

Multiscale feature pyramid network based on activity level weight selection for infrared and visible image fusion

Rui Xu, Gang Liu, Yuning Xie, Bavirisetti Durga Prasad, Yao Qian, and Mengliang Xing
J. Opt. Soc. Am. A 39(12) 2193-2204 (2022)

PFNet: an unsupervised deep network for polarization image fusion

Junchao Zhang, Jianbo Shao, Jianlai Chen, Degui Yang, Buge Liang, and Rongguang Liang
Opt. Lett. 45(6) 1507-1510 (2020)

Infrared and visible image fusion algorithm based on a cross-layer densely connected convolutional network

Ruixing Yu, Weiyu Chen, and Bing Zhu
Appl. Opt. 61(11) 3107-3114 (2022)