Multispectral and Hyperspectral Image Fusion (MHIF) is a practical task that aims to fuse a high-resolution multispectral image (HR-MSI) and a low-resolution hyperspectral image (LR-HSI) of the same scene to obtain a high-resolution hyperspectral image (HR-HSI). Benefiting from powerful inductive bias capability, CNN-based methods have achieved great success in the MHIF task. However, they lack certain interpretability and require convolution structures be stacked to enhance performance. Recently, Implicit Neural Representation (INR) has achieved good performance and interpretability in 2D tasks due to its ability to locally interpolate samples and utilize multimodal content such as pixels and coordinates. Although INR-based approaches show promise, they require extra construction of high-frequency information (\emph{e.g.,} positional encoding). In this paper, inspired by previous work of MHIF task, we realize that HR-MSI could serve as a high-frequency detail auxiliary input, leading us to propose a novel INR-based hyperspectral fusion function named Implicit Neural Feature Fusion Function (INF). As an elaborate structure, it solves the MHIF task and addresses deficiencies in the INR-based approaches. Specifically, our INF designs a Dual High-Frequency Fusion (DHFF) structure that obtains high-frequency information twice from HR-MSI and LR-HSI, then subtly fuses them with coordinate information. Moreover, the proposed INF incorporates a parameter-free method named INR with cosine similarity (INR-CS) that uses cosine similarity to generate local weights through feature vectors. Based on INF, we construct an Implicit Neural Fusion Network (INFN) that achieves state-of-the-art performance for MHIF tasks of two public datasets, \emph{i.e.,} CAVE and Harvard. The code will soon be made available on GitHub.

翻译：多光谱与高光谱图像融合（MHIF）是一项实用任务，旨在融合同一场景的高分辨率多光谱图像（HR-MSI）和低分辨率高光谱图像（LR-HSI），从而获得高分辨率高光谱图像（HR-HSI）。得益于强大的归纳偏置能力，基于CNN的方法在MHIF任务中取得了显著成功。然而，这类方法缺乏可解释性，且需要通过堆叠卷积结构来提升性能。近年来，隐式神经表示（INR）凭借其局部插值采样以及利用像素、坐标等多模态内容的能力，在二维任务中展现出良好性能与可解释性。尽管基于INR的方法前景可观，但需额外构建高频信息（如位置编码）。本文受前人MHIF任务研究的启发，意识到HR-MSI可作为高频细节辅助输入，进而提出一种新颖的基于INR的超光谱融合函数——隐式神经特征融合函数（INF）。该精巧结构不仅解决了MHIF任务，还弥补了基于INR方法的不足。具体而言，INF设计了一种双高频融合（DHFF）结构，通过HR-MSI和LR-HSI两次获取高频信息，并将其与坐标信息巧妙融合。此外，所提出的INF引入了一种名为基于余弦相似度的隐式神经表示（INR-CS）的无参数方法，利用余弦相似度通过特征向量生成局部权重。基于INF，我们构建了隐式神经融合网络（INFN），在CAVE和Harvard两个公开数据集的MHIF任务中达到了当前最优性能。相关代码即将在GitHub上开源。