Saved in:
Bibliographic Details
Main Authors: Yang, Kaixuan, Xiang, Wei, Chen, Zhenshuai, Jin, Tong, Liu, Yunpeng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.13067
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 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.