PEFuse: Progressive Emphasis of Dual-Frequency Feature for Infrared and Visible Image Fusion

Infrared and Visible Image Fusion (IVF) is a fine grained cross-modal technique that integrates thermal cuesfrom infrared images with detailed textures from visible images at the pixel level, enhancing visual quality and downstream task performance. However, existing methods for dual-frequency feature decoupling and fusion often lack effective high-frequency separation and sufficient interaction between high- and low-frequency features, limiting the preservation of fine textures and structural details. To address these challenges, we propose PEFuse, a framework for Progressive Emphasis of Dual-Frequency Feature in IVF. Specifically, PEFuse employs a Discrete Cosine Transform-based High Frequency Extractor (DCT-HFE) to disentangle texture and edge information, followed by a Cross Modulation Collaborative Fusion (CMCF) module that strengthens the complementarity between frequency components during early fusion. For frequency-specific refinement, we design a Multi-Kernel Weighted Convolution (MK WConv) to enhance high-frequency details and a Downsample Top KSelf-Attention (DTKSA) to capture low-frequency global context. Furthermore, an Enhanced Attention Fusion (EAF) module is integrated to progressively and adaptively guide the interaction and integration of frequency features throughout the fusion pipeline. Experimental results demonstrate that PEFuse achieves state-of the-art fusion quality on standard infrared-visible benchmarks and significantly improves performance in downstream tasks such as object detection. The code will be made publicly available later at https://github.com/zocern/PEFuse.