ConvFuse: A Progressive Convformer Network for Context-Aware Multisensor Image Fusion

Multisensor image fusion aims to generate a high-quality composite image by integrating information from diverse sources. While deep learning-based approaches enhance fusion quality, they often suffer from high computational costs and information loss due to single-step feature integration. We propose ConvFuse, a lightweight DL framework for infrared and visible image fusion. Our context-aware convformer block effectively preserves local-global and contextual details without relying on attention mechanisms. A progressive intermodality fusion strategy enhances modality-specific features, while a multiscale decoder ensures seamless feature integration across different scales. Experimental results on benchmark datasets show that ConvFuse surpasses transformer-based and SOTA DL-based methods in fusion quality and efficiency.