Saved in:
Bibliographic Details
Main Authors: Yang, Zhiqi, Xiao, Jin-Liang, Yin, Shan, Deng, Liang-Jian, Vivone, Gemine
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.08903
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911580810117120
author Yang, Zhiqi
Xiao, Jin-Liang
Yin, Shan
Deng, Liang-Jian
Vivone, Gemine
author_facet Yang, Zhiqi
Xiao, Jin-Liang
Yin, Shan
Deng, Liang-Jian
Vivone, Gemine
contents Pansharpening aims to generate high-resolution multispectral (HRMS) images by fusing low-resolution multispectral (LRMS) and high-resolution panchromatic (PAN) images while preserving both spectral and spatial information. Although deep learning (DL)-based pansharpening methods achieve impressive performance, they require high training cost and large datasets, and often degrade when the test distribution differs from training, limiting generalization. Recent zero-shot methods, trained on a single PAN/LRMS pair, offer strong generalization but suffer from limited fusion quality, high computational overhead, and slow convergence. To address these issues, we propose FMG-Pan, a fast and generalizable model-guided instance-wise adaptation framework for real-world pansharpening, achieving both cross-sensor generality and rapid training-inference. The framework leverages a pretrained model to guide a lightweight adaptive network through joint optimization with spectral and physical fidelity constraints. We further design a novel physical fidelity term to enhance spatial detail preservation. Extensive experiments on real-world datasets under both intra- and cross-sensor settings demonstrate state-of-the-art performance. On the WorldView-3 dataset, FMG-Pan completes training and inference for a 512x512x8 image within 3 seconds on an RTX 3090 GPU, significantly faster than existing zero-shot methods, making it suitable for practical deployment.
format Preprint
id arxiv_https___arxiv_org_abs_2604_08903
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Fast Model-guided Instance-wise Adaptation Framework for Real-world Pansharpening with Fidelity Constraints
Yang, Zhiqi
Xiao, Jin-Liang
Yin, Shan
Deng, Liang-Jian
Vivone, Gemine
Computer Vision and Pattern Recognition
Pansharpening aims to generate high-resolution multispectral (HRMS) images by fusing low-resolution multispectral (LRMS) and high-resolution panchromatic (PAN) images while preserving both spectral and spatial information. Although deep learning (DL)-based pansharpening methods achieve impressive performance, they require high training cost and large datasets, and often degrade when the test distribution differs from training, limiting generalization. Recent zero-shot methods, trained on a single PAN/LRMS pair, offer strong generalization but suffer from limited fusion quality, high computational overhead, and slow convergence. To address these issues, we propose FMG-Pan, a fast and generalizable model-guided instance-wise adaptation framework for real-world pansharpening, achieving both cross-sensor generality and rapid training-inference. The framework leverages a pretrained model to guide a lightweight adaptive network through joint optimization with spectral and physical fidelity constraints. We further design a novel physical fidelity term to enhance spatial detail preservation. Extensive experiments on real-world datasets under both intra- and cross-sensor settings demonstrate state-of-the-art performance. On the WorldView-3 dataset, FMG-Pan completes training and inference for a 512x512x8 image within 3 seconds on an RTX 3090 GPU, significantly faster than existing zero-shot methods, making it suitable for practical deployment.
title Fast Model-guided Instance-wise Adaptation Framework for Real-world Pansharpening with Fidelity Constraints
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.08903