DAF-Net: A Dual-Branch Feature Decomposition Fusion Network with Domain Adaptive for Infrared and Visible Image Fusion

TL;DR

DAF-Net is a novel dual-branch neural network that effectively fuses infrared and visible images by aligning feature spaces with domain adaptation, leading to superior fusion quality and scene understanding.

Contribution

Introduces a dual-branch feature decomposition fusion network with domain adaptive MK-MMD for improved infrared and visible image fusion.

Findings

Outperforms existing methods on multiple datasets

Enhances visual quality and detail preservation

Effectively aligns feature spaces of different modalities

Abstract

Infrared and visible image fusion aims to combine complementary information from both modalities to provide a more comprehensive scene understanding. However, due to the significant differences between the two modalities, preserving key features during the fusion process remains a challenge. To address this issue, we propose a dual-branch feature decomposition fusion network (DAF-Net) with domain adaptive, which introduces Multi-Kernel Maximum Mean Discrepancy (MK-MMD) into the base encoder and designs a hybrid kernel function suitable for infrared and visible image fusion. The base encoder built on the Restormer network captures global structural information while the detail encoder based on Invertible Neural Networks (INN) focuses on extracting detail texture information. By incorporating MK-MMD, the DAF-Net effectively aligns the latent feature spaces of visible and infrared images, thereby improving the quality of the fused images. Experimental results demonstrate that the proposed method outperforms existing techniques across multiple datasets, significantly enhancing both visual quality and fusion performance. The related Python code is available at https://github.com/xujian000/DAF-Net.