神经动力学驱动的耦合神经P系统用于多聚焦图像融合
Neurodynamics-Driven Coupled Neural P Systems for Multi-Focus Image Fusion
用脉冲发放计数直接生成边界精确的决策图、免去后处理，这一思路可迁移到其他需要像素级二值决策的低层融合任务（如曝光融合、去雾中的区域选择），并为用生物可解释模型替代黑盒融合网络提供参考。
原文依据 ND-CNPFuse distinguishes between focused and unfocused regions by mapping the source image into interpretable spike matrices
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论多聚焦图像融合（MFIF）是图像处理中的一项关键技术，其核心挑战在于生成边界精确的决策图。然而，基于启发式规则的传统方法以及采用黑盒网络的深度学习方法都难以生成高质量的决策图。为克服这一挑战，我们引入神经动力学驱动的耦合神经P（CNP）系统——一种受脉冲机制启发的生物神经计算模型——以提升决策图的准确性。具体而言，我们首先对模型的神经动力学进行深入分析，以确定网络参数与输入信号之间的约束关系。这一扎实的分析避免了神经元的异常连续发放，并确保模型能够准确区分聚焦区域与非聚焦区域，从而为MFIF生成高质量的决策图。基于该分析，我们提出了面向这一具有挑战性的MFIF任务的神经动力学驱动CNP融合模型（ND-CNPFuse）。与现有的决策图生成思路不同，ND-CNPFuse通过将源图像映射为可解释的脉冲矩阵来区分聚焦区域与非聚焦区域。通过比较脉冲数量，可以直接生成准确的决策图，而无需任何后处理。大量实验结果表明，ND-CNPFuse在Lytro、MFFW、MFI-WHU和Real-MFF四个经典MFIF数据集上取得了新的最优性能。代码已发布于 https://github.com/MorvanLi/ND-CNPFuse。
英文原文摘要 1550 字符
Multi-focus image fusion (MFIF) is a crucial technique in image processing, with a key challenge being the generation of decision maps with precise boundaries. However, traditional methods based on heuristic rules and deep learning methods with black-box networks are difficult to generate high-quality decision maps. To overcome this challenge, we introduce neurodynamics-driven coupled neural P (CNP) systems, which are biological neural computation models inspired by spiking mechanisms, to enhance the accuracy of decision maps. Specifically, we first conduct an in-depth analysis of the model's neurodynamics to identify the constraints between the network parameters and the input signals. This solid analysis avoids abnormal continuous firing of neurons and ensures the model accurately distinguishes between focused and unfocused regions, generating high-quality decision maps for MFIF. Based on this analysis, we propose a Neurodynamics-Driven CNP Fusion model (ND-CNPFuse) tailored for the challenging MFIF task. Unlike current ideas of decision map generation, ND-CNPFuse distinguishes between focused and unfocused regions by mapping the source image into interpretable spike matrices. By comparing the number of spikes, an accurate decision map can be generated directly without any post-processing. Extensive experimental results show that ND-CNPFuse achieves new state-of-the-art performance on four classical MFIF datasets, including Lytro, MFFW, MFI-WHU, and Real-MFF. The code is available at https://github.com/MorvanLi/ND-CNPFuse.