一分钟训练实现跨域图像融合，零样本泛化能力强
Hybrid Fusion: One-Minute Efficient Training for Zero-Shot Cross-Domain Image Fusion
- 用可学习U-Net生成动态引导图，控制经典拉普拉斯金字塔融合
- 在RTX 4090上1分钟完成全分辨率训练，性能媲美当前最佳
- 无需预训练模型，适合医疗、红外可见光等关键领域应用
图像融合旨在将多源互补信息整合为一张更优图像。传统方法虽快速但适应性差，深度学习方法虽达前沿性能却存在训练慢、资源消耗大、依赖分块训练导致推理效率低的问题。本文提出一种新型混合框架：通过可学习的U-Net生成动态引导图，驱动固定的拉普拉斯金字塔融合核。该策略解耦了策略学习与像素合成，实现高效的全分辨率训练，彻底消除训练-推理差距。模型在RTX 4090上仅需约1分钟即可从零训练完成，消费级笔记本GPU上约2分钟，性能媲美当前最优（SOTA），且具备强大零样本跨任务泛化能力，涵盖红外-可见光到医学影像等多种场景。融合输出完全由源图像线性构建，确保关键应用下的高保真性。代码已开源。
原文摘要 · Abstract (English)
Image fusion seeks to integrate complementary information from multiple sources into a single, superior image. While traditional methods are fast, they lack adaptability and performance. Conversely, deep learning approaches achieve state-of-the-art (SOTA) results but suffer from critical inefficiencies: their reliance on slow, resource-intensive, patch-based training introduces a significant gap with full-resolution inference. We propose a novel hybrid framework that resolves this trade-off. Our method utilizes a learnable U-Net to generate a dynamic guidance map that directs a classic, fixed Laplacian pyramid fusion kernel. This decoupling of policy learning from pixel synthesis enables remarkably efficient full-resolution training, eliminating the train-inference gap. Consequently, our model achieves SOTA-comparable performance in about one minute on a RTX 4090 or two minutes on a consumer laptop GPU from scratch without any external model and demonstrates powerful zero-shot generalization across diverse tasks, from infrared-visible to medical imaging. By design, the fused output is linearly constructed solely from source information, ensuring high faithfulness for critical applications. The codes are available at https://github.com/Zirconium233/HybridFusion
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。