Infrared and visible image fusion via global variable consensus

Abstract

In this paper, we propose an infrared and visible image fusion framework based on the consensus problem. Most current infrared and visible image fusion models aim to transfer only one characteristic of each source domain to the final fusion result. This mechanism limits the performances of fusion algorithms under different conditions. We present a general fusion framework based to solve the global variable consensus optimization problem through altering direction method of multipliers (ADMM). We identified that combination of the local operators allows smooth transfer of superficial characteristics of the source domain into the fusion result. Our modification of ADMM enables us to expand the fusion algorithm's compatibility by tackling various setting including dimensionality, data types and style. The qualitative and quantitative experiment results demonstrate that, compared with other state-of-the-art algorithms, the proposed method can provide competitive performance in transferring features, structures, and information from source images to fusion results.