Fast infrared and visible image fusion with structural decomposition

作者：

Highlights：

• We are the first to use structural patch decomposition for infrared and visible image fusion.

• The proposed method is fast, whose computational cost is independent of patch size.

• The relationship with other filtering based methods for infrared and visible image fusion is analyzed.

• The multi-scale technique is leveraged to reduce the halo and inconsistency artifacts.

摘要

•We are the first to use structural patch decomposition for infrared and visible image fusion.•The proposed method is fast, whose computational cost is independent of patch size.•The relationship with other filtering based methods for infrared and visible image fusion is analyzed.•The multi-scale technique is leveraged to reduce the halo and inconsistency artifacts.

论文关键词：Image fusion,Multi-scale,Fast fusion,Structural decomposition,Infrared

论文评审过程：Received 4 April 2020, Revised 18 June 2020, Accepted 22 June 2020, Available online 27 June 2020, Version of Record 30 June 2020.

论文官网地址：https://doi.org/10.1016/j.knosys.2020.106182