Pansharpening is a crucial remote sensing technique that fuses low-resolution multispectral (LRMS) images with high-resolution panchromatic (PAN) images to generate high-resolution multispectral (HRMS) imagery. Although deep learning techniques have significantly advanced pansharpening, many existing methods suffer from limited cross-sensor generalization and high computational overhead, restricting their real-time applications. To address these challenges, we propose an efficient framework that quickly adapts to a specific input instance, completing both training and inference in a short time. Our framework splits the input image into multiple patches, selects a subset for unsupervised CAT training, and then performs inference on all patches, stitching them into the final output. The CAT module, integrated between the feature extraction and channel transformation stages of a pre-trained network, tailors the fused features and fixes the parameters for efficient inference, generating improved results. Our approach offers two key advantages: (1) : by mitigating cross-sensor degradation, our model--although pre-trained on a specific dataset--achieves superior performance on datasets captured by other sensors; (2) : the CAT-enhanced network can swiftly adapt to the test sample using the single LRMS-PAN pair input, without requiring extensive large-scale data retraining. Experiments on the real-world data from WorldView-3 and WorldView-2 datasets demonstrate that our method achieves state-of-the-art performance on cross-sensor real-world data, while achieving both training and inference of image within and image within at the fastest setting on a commonly used RTX 3090 GPU.
View on arXiv@article{xin2025_2504.10242,
title={ CAT: A Conditional Adaptation Tailor for Efficient and Effective Instance-Specific Pansharpening on Real-World Data },
author={ Tianyu Xin and Jin-Liang Xiao and Zeyu Xia and Shan Yin and Liang-Jian Deng },
journal={arXiv preprint arXiv:2504.10242},
year={ 2025 }
}