Direction-aware multi-scale gradient loss for infrared and visible image fusion
This addresses edge fidelity issues in image fusion for applications like surveillance or medical imaging, but is incremental as it modifies only the loss function within existing frameworks.
The paper tackles the problem of preserving directional information in infrared and visible image fusion by introducing a direction-aware, multi-scale gradient loss that supervises horizontal and vertical components separately with sign preservation, resulting in sharper edges and richer texture without architectural changes.
Infrared and visible image fusion aims to integrate complementary information from co-registered source images to produce a single, informative result. Most learning-based approaches train with a combination of structural similarity loss, intensity reconstruction loss, and a gradient-magnitude term. However, collapsing gradients to their magnitude removes directional information, yielding ambiguous supervision and suboptimal edge fidelity. We introduce a direction-aware, multi-scale gradient loss that supervises horizontal and vertical components separately and preserves their sign across scales. This axis-wise, sign-preserving objective provides clear directional guidance at both fine and coarse resolutions, promoting sharper, better-aligned edges and richer texture preservation without changing model architectures or training protocols. Experiments on open-source model and multiple public benchmarks demonstrate effectiveness of our approach.