One Model for ALL: Low-Level Task Interaction Is a Key to Task-Agnostic Image Fusion

TL;DR

This paper introduces GIFNet, a versatile image fusion model that leverages low-level pixel interactions for improved task-agnostic performance across diverse scenarios, including unseen data and single-modality enhancement.

Contribution

The paper proposes a novel low-level task interaction paradigm for image fusion, enabling a single model to handle multiple fusion tasks without relying on high-level semantic bridging.

Findings

Supports diverse fusion tasks with high performance

Effective in both seen and unseen scenarios

Enables single-modality enhancement

Abstract

Advanced image fusion methods mostly prioritise high-level missions, where task interaction struggles with semantic gaps, requiring complex bridging mechanisms. In contrast, we propose to leverage low-level vision tasks from digital photography fusion, allowing for effective feature interaction through pixel-level supervision. This new paradigm provides strong guidance for unsupervised multimodal fusion without relying on abstract semantics, enhancing task-shared feature learning for broader applicability. Owning to the hybrid image features and enhanced universal representations, the proposed GIFNet supports diverse fusion tasks, achieving high performance across both seen and unseen scenarios with a single model. Uniquely, experimental results reveal that our framework also supports single-modality enhancement, offering superior flexibility for practical applications. Our code will be available at https://github.com/AWCXV/GIFNet.