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.
@article{arxiv.2510.13067,
title = {Direction-aware multi-scale gradient loss for infrared and visible image fusion},
author = {Kaixuan Yang and Wei Xiang and Zhenshuai Chen and Tong Jin and Yunpeng Liu},
journal= {arXiv preprint arXiv:2510.13067},
year = {2025}
}