提升红外可见光图像融合的边缘清晰度与纹理保真度
Direction-aware multi-scale gradient loss for infrared and visible image fusion
- 分离监督水平与垂直梯度方向，保留符号信息
- 在多尺度上增强边缘对齐，显著提升细节还原
- 无需修改模型或训练流程，适配各类融合网络
红外与可见光图像融合旨在整合配准源图像中的互补信息，生成单一信息丰富的结果。现有基于学习的方法通常采用结构相似性损失、强度重建损失及梯度幅值项组合训练。然而，将梯度合并为幅值会丢失方向信息，导致监督模糊，边缘保真度下降。本文提出一种方向感知的多尺度梯度损失，分别监督水平和垂直分量，并在多尺度下保持其符号。该轴向、符号保留的目标在细粒度与粗粒度分辨率下均提供明确的方向引导，促进更锐利、对齐更好的边缘以及更丰富的纹理保留，且无需改变模型架构或训练协议。在开源模型及多个公开基准上的实验验证了方法的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。