Multi-Focus Image Fusion (MFIF) is a promising image enhancement technique to generate all-in-focus images meeting visual needs, and it is a precondition for other computer vision tasks. One emergent research trend in MFIF involves approaches to avoiding a defocus spread effect (DSE) around a focus/defocus boundary (FDB). This study proposes a generative adversarial network for MFIF tasks called MFIF-GAN, to attenuate the DSE by generating focus maps in which the foreground region is correctly larger than corresponding objects. A Squeeze and Excitation residual module is employed in the proposed network. By combining prior knowledge of a training condition, the network is trained on a synthetic dataset based on an $\alpha$-matte model. In addition, reconstruction and gradient regularization terms are combined in the loss functions to enhance boundary details and improve the quality of fused images. Extensive experiments demonstrate that the MFIF-GAN outperforms eight state-of-the-art (SOTA) methods in visual perception and quantitative analysis, as well as efficiency. Moreover, an edge diffusion and contraction module is proposed to verify that focus maps generated by our method are accurate at the pixel level.

多焦点图像融合（MFIF）是一种有前途的图像增强技术，可以生成满足视觉需求的全焦点图像，它是其他计算机视觉任务的前提。MFIF中的一种新兴研究趋势涉及避免聚焦/散焦边界（FDB）周围的散焦扩散效应（DSE）的方法。这项研究针对MFIF任务提出了一种生成对抗网络，称为MFIF-GAN，以通过生成聚焦图来衰减DSE，在聚焦图中前景区域正确地大于对应的对象。甲挤压和励磁残余模块采用所提出的网络。通过结合训练条件的先验知识，可以在基于$\alpha$哑光模型。另外，在损失函数中结合了重构和梯度正则项，以增强边界细节并提高融合图像的质量。广泛的实验表明，MFIF-GAN在视觉感知和定量分析以及效率方面均优于八种最先进的（SOTA）方法。此外，提出了一种边缘扩散和收缩模块，以验证通过我们的方法生成的聚焦图在像素级别上是准确的。