Polarization image fusion with self-learned fusion strategy

作者：

Highlights：

• A new unsupervised fusion network by integrating a Fusion Sub-Net is proposed.

• A novel loss function is performed to address fusion problems.

• The trained network on polarization data works well on other fusion tasks.

摘要

•A new unsupervised fusion network by integrating a Fusion Sub-Net is proposed.•A novel loss function is performed to address fusion problems.•The trained network on polarization data works well on other fusion tasks.

论文关键词：Image fusion,Encoder-Decoder,Polarization image,Unsupervised learning

论文评审过程：Received 1 June 2020, Revised 20 April 2021, Accepted 11 May 2021, Available online 20 May 2021, Version of Record 29 May 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108045