Saved in:
Bibliographic Details
Main Authors: Zhu, Anqi, Ma, Mengting, Jiang, Yizhen, Li, Xiangdong, Zheng, Kai, Li, Jiaxin, Zhang, Wei
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.12463
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917406636507136
author Zhu, Anqi
Ma, Mengting
Jiang, Yizhen
Li, Xiangdong
Zheng, Kai
Li, Jiaxin
Zhang, Wei
author_facet Zhu, Anqi
Ma, Mengting
Jiang, Yizhen
Li, Xiangdong
Zheng, Kai
Li, Jiaxin
Zhang, Wei
contents Pansharpening aims to synthesize high-resolution multispectral (HR-MS) images by fusing the spatial textures of panchromatic (PAN) images with the spectral information of low-resolution multispectral (LR-MS) images. While recent deep learning paradigms, especially diffusion-based operators, have pushed the performance boundaries, they often encounter spectral-spatial blurring and prohibitive computational costs due to their stochastic nature and iterative sampling. In this paper, we propose the Euler-inspired Decoupling Neural Operator (EDNO), a physics-inspired framework that redefines pansharpening as a continuous functional mapping in the frequency domain. Departing from conventional Cartesian feature processing, our EDNO leverages Euler's formula to transform features into a polar coordinate system, enabling a novel explicit-implicit interaction mechanism. Specifically, we develop the Euler Feature Interaction Layer (EFIL), which decouples the fusion task into two specialized modules: 1) Explicit Feature Interaction Module, utilizing a linear weighting scheme to simulate phase rotation for adaptive geometric alignment; and 2) Implicit Feature Interaction Module, employing a feed-forward network to model spectral distributions for superior color consistency. By operating in the frequency domain, EDNO inherently captures global receptive fields while maintaining discretization-invariance. Experimental results on the three datasets demonstrate that EDNO offers a superior efficiency-performance balance compared to heavyweight architectures.
format Preprint
id arxiv_https___arxiv_org_abs_2604_12463
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Euler-inspired Decoupling Neural Operator for Efficient Pansharpening
Zhu, Anqi
Ma, Mengting
Jiang, Yizhen
Li, Xiangdong
Zheng, Kai
Li, Jiaxin
Zhang, Wei
Computer Vision and Pattern Recognition
Artificial Intelligence
Pansharpening aims to synthesize high-resolution multispectral (HR-MS) images by fusing the spatial textures of panchromatic (PAN) images with the spectral information of low-resolution multispectral (LR-MS) images. While recent deep learning paradigms, especially diffusion-based operators, have pushed the performance boundaries, they often encounter spectral-spatial blurring and prohibitive computational costs due to their stochastic nature and iterative sampling. In this paper, we propose the Euler-inspired Decoupling Neural Operator (EDNO), a physics-inspired framework that redefines pansharpening as a continuous functional mapping in the frequency domain. Departing from conventional Cartesian feature processing, our EDNO leverages Euler's formula to transform features into a polar coordinate system, enabling a novel explicit-implicit interaction mechanism. Specifically, we develop the Euler Feature Interaction Layer (EFIL), which decouples the fusion task into two specialized modules: 1) Explicit Feature Interaction Module, utilizing a linear weighting scheme to simulate phase rotation for adaptive geometric alignment; and 2) Implicit Feature Interaction Module, employing a feed-forward network to model spectral distributions for superior color consistency. By operating in the frequency domain, EDNO inherently captures global receptive fields while maintaining discretization-invariance. Experimental results on the three datasets demonstrate that EDNO offers a superior efficiency-performance balance compared to heavyweight architectures.
title Euler-inspired Decoupling Neural Operator for Efficient Pansharpening
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2604.12463