超越所见：通过语义-像素熵权衡实现零样本泛化的统一图像融合框架
More Than Meets the Eye: A Unified Image Fusion Framework via Semantic-Pixel Entropy Trade-off for Zero-Shot Generalization
提出基于自由能原理的语义-像素熵权衡范式与频率感知特征解耦机制，可复用于多模态图像融合、零样本泛化到未见融合任务，并为无监督融合提供统一优化目标。
原文依据 we introduce a fusion paradigm that combines high pixel-entropy expectation with low semantic-entropy expectation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现有图像融合方法难以适应未见过的融合任务，并且在平衡语义信息与像素级细节方面存在局限。这一局限可归因于三个关键挑战：（1）缺乏统一且任务无关的优化目标；（2）平衡语义保真度与像素级丰富度本身存在困难；（3）过度依赖监督学习，限制了跨任务的可迁移性。为解决这些问题，本文提出一个统一的融合框架，即使仅使用红外-可见光图像对进行训练，也能泛化到多种融合任务。具体而言，受自由能原理启发，我们引入一种融合范式，将高像素熵期望与低语义熵期望相结合，并设计频率感知的特征解耦机制以平衡语义内容与像素细节。此外，一种无监督双路径权衡策略在语义和像素两个层面提供协同约束。实验表明，我们的方法在视觉质量和下游任务性能上显著优于现有最优方法。它不仅能高效处理已训练任务，还能很好地泛化到未见过的融合任务，同时具有轻量级模型参数和较强的实际适用性。代码见 https://github.com/XiaoW-Liu/DECC。
英文原文摘要 1419 字符
Existing image fusion methods face difficulties in adapting to unseen fusion tasks and have limitations in balancing semantic information with pixel-level details. This limitation can be attributed to three key challenges: (1) the lack of a unified, task-agnostic optimization objective; (2) the inherent difficulty in balancing semantic fidelity and pixel-level richness; and (3) an over-reliance on supervised learning, which limits transferability across tasks. To overcome these issues, this work proposes a unified fusion framework that generalizes to diverse fusion tasks even when trained solely on infrared-visible image pairs. Specifically, inspired by the free-energy principle, we introduce a fusion paradigm that combines high pixel-entropy expectation with low semantic-entropy expectation, and we design a frequency-aware feature decoupling mechanism to balance semantic content and pixel detail. Furthermore, an unsupervised dual-path trade-off strategy provides collaborative constraints at both semantic and pixel levels. Experiments show that our method significantly outperforms existing state-of-the-art methods in visual quality and downstream-task performance. It not only handles trained tasks efficiently but also generalizes well to unseen fusion tasks, while featuring lightweight model parameters and strong practical applicability. The code is available at https://github.com/XiaoW-Liu/DECC.