Abstract

To preserve the saliency of targets in infrared images and the textures in visible images, a novel infrared and visible image fusion method, to the best of our knowledge, is proposed. First, we design a densely connected convolutional network that contains an encoder, fusion, and decoder to minimize the omission of source image effective information. Then, a loss function based on the variational model is designed to retain the thermal radiation information of the infrared image and the details of the visible image to the greatest extent. The experimental results show that the proposed method outperforms state-of-the-art methods in terms of six metrics and better preserves the clear target and textures of infrared and visible images.

© 2022 Optica Publishing Group

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)

Infrared and visible image fusion using salient decomposition based on a generative adversarial network

Lei Chen and Jun Han
Appl. Opt. 60(23) 7017-7026 (2021)

Unsupervised end-to-end infrared and visible image fusion network using learnable fusion strategy

Yili Chen, Minjie Wan, Yunkai Xu, Xiqing Cao, Xiaojie Zhang, Qian Chen, and Guohua Gu
J. Opt. Soc. Am. A 39(12) 2257-2270 (2022)

Adaptive brightness fusion method for intraoperative near-infrared fluorescence and visible images

Chong Zhang, Kun Wang, and Jie Tian
Biomed. Opt. Express 13(3) 1243-1260 (2022)

Image fusion using a multi-level image decomposition and fusion method

Yu Tian, Wenjing Yang, and Ji Wang
Appl. Opt. 60(24) 7466-7479 (2021)