# Hybrid Fusion: One-Minute Efficient Training for Zero-Shot Cross-Domain Image Fusion

arXiv: https://arxiv.org/abs/2602.20851 · HTML: https://mlsanity.com/paper/2602.20851/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 27 references that are in the map.
- First posted on arXiv 24 Feb 2026.

## Builds on (most cited first, 9 of 9)

- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection](https://mlsanity.com/paper/2203.16220/) (2022)
- [CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion](https://mlsanity.com/paper/2211.14461/) (2022)
- [DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion](https://mlsanity.com/paper/2303.06840/) (2023)
- [Text-IF: Leveraging Semantic Text Guidance for Degradation-Aware and Interactive Image Fusion](https://mlsanity.com/paper/2403.16387/) (2024)
- [Task-Customized Mixture of Adapters for General Image Fusion](https://mlsanity.com/paper/2403.12494/) (2024)
- [Image Fusion in Remote Sensing: An Overview and Meta Analysis](https://mlsanity.com/paper/2401.08837/) (2024)
- [VideoFusion: A Spatio-Temporal Collaborative Network for Multi-modal Video Fusion](https://mlsanity.com/paper/2503.23359/) (2025)
- [Distilling Textual Priors from LLM to Efficient Image Fusion](https://mlsanity.com/paper/2504.07029/) (2025)

## Abstract (arXiv)

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