Although remarkable progress has been made in recent years, current multi-exposure image fusion (MEF) research is still bounded by the lack of real ground truth, objective evaluation function, and robust fusion strategy. In this paper, we study the MEF problem from a new perspective. We don't utilize any synthesized ground truth, design any loss function, or develop any fusion strategy. Our proposed method EMEF takes advantage of the wisdom of multiple imperfect MEF contributors including both conventional and deep learning-based methods. Specifically, EMEF consists of two main stages: pre-train an imitator network and tune the imitator in the runtime. In the first stage, we make a unified network imitate different MEF targets in a style modulation way. In the second stage, we tune the imitator network by optimizing the style code, in order to find an optimal fusion result for each input pair. In the experiment, we construct EMEF from four state-of-the-art MEF methods and then make comparisons with the individuals and several other competitive methods on the latest released MEF benchmark dataset. The promising experimental results demonstrate that our ensemble framework can "get the best of all worlds". The code is available at https://github.com/medalwill/EMEF.

翻译：尽管近年来取得了显著进展，当前的多曝光图像融合（MEF）研究仍然受限于缺乏真实标注、客观评价函数以及鲁棒融合策略。本文从一个全新视角研究MEF问题。我们既不使用任何合成真值，也不设计任何损失函数，更不开发任何融合策略。所提出的EMEF方法利用了多个包括传统方法和深度学习方法在内的不完美MEF贡献者的智慧。具体而言，EMEF包含两个主要阶段：预训练模仿器网络与运行时调优模仿器。第一阶段，我们以风格调制的方式使统一网络模仿不同MEF目标。第二阶段，通过优化风格代码调优模仿器网络，从而为每对输入图像寻找最优融合结果。实验中，我们基于四种最先进的MEF方法构建EMEF，并与各成员方法及其他多种竞争方法在最新发布的MEF基准数据集上进行对比。令人鼓舞的实验结果表明，我们的集成框架能够"集各家所长"。代码已开源至https://github.com/medalwill/EMEF。