# Fast Model-guided Instance-wise Adaptation Framework for Real-world Pansharpening with Fidelity Constraints

arXiv: https://arxiv.org/abs/2604.08903 · HTML: https://mlsanity.com/paper/2604.08903/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 41 references that are in the map.
- First posted on arXiv 10 Apr 2026.

## Builds on (most cited first, 4 of 4)

- [Pansharpening via Detail Injection Based Convolutional Neural Networks](https://mlsanity.com/paper/1806.08898/) (2018)
- [PanFormer: a Transformer Based Model for Pan-sharpening](https://mlsanity.com/paper/2203.02916/) (2022)
- [Pansharpening by convolutional neural networks in the full resolution framework](https://mlsanity.com/paper/2111.08334/) (2021)
- [Wavelet-Assisted Multi-Frequency Attention Network for Pansharpening](https://mlsanity.com/paper/2502.04903/) (2025)

## Abstract (arXiv)

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.