Explicit and implicit models in infrared and visible image fusion

TL;DR

This paper compares explicit and implicit deep learning models for infrared and visible image fusion, highlighting their strengths and limitations in feature preservation and stability, and discusses future research directions.

Contribution

It introduces a comparison of explicit and implicit models in multi-modal image fusion, analyzing their capabilities and challenges based on extensive experiments.

Findings

Implicit models better learn image features

Explicit models are more stable

Implicit models need improved stability

Abstract

Infrared and visible images, as multi-modal image pairs, show significant differences in the expression of the same scene. The image fusion task is faced with two problems: one is to maintain the unique features between different modalities, and the other is to maintain features at various levels like local and global features. This paper discusses the limitations of deep learning models in image fusion and the corresponding optimization strategies. Based on artificially designed structures and constraints, we divide models into explicit models, and implicit models that adaptively learn high-level features or can establish global pixel associations. Ten models for comparison experiments on 21 test sets were screened. The qualitative and quantitative results show that the implicit models have more comprehensive ability to learn image features. At the same time, the stability of them needs to be improved. Aiming at the advantages and limitations to be solved by existing algorithms, we discuss the main problems of multi-modal image fusion and future research directions.