Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.07369 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908665773031424 |
|---|---|
| author | Xin, Tianyu Xiao, Jin-Liang Xia, Zeyu Yin, Shan Deng, Liang-Jian |
| author_facet | Xin, Tianyu Xiao, Jin-Liang Xia, Zeyu Yin, Shan Deng, Liang-Jian |
| contents | Deep learning methods for pansharpening have advanced rapidly, yet models pretrained on data from a specific sensor often generalize poorly to data from other sensors. Existing methods to tackle such cross-sensor degradation include retraining model or zero-shot methods, but they are highly time-consuming or even need extra training data. To address these challenges, our method first performs modular decomposition on deep learning-based pansharpening models, revealing a general yet critical interface where high-dimensional fused features begin mapping to the channel space of the final image. % may need revisement A Feature Tailor is then integrated at this interface to address cross-sensor degradation at the feature level, and is trained efficiently with physics-aware unsupervised losses. Moreover, our method operates in a patch-wise manner, training on partial patches and performing parallel inference on all patches to boost efficiency. Our method offers two key advantages: (1) $\textit{Improved Generalization Ability}$: it significantly enhance performance in cross-sensor cases. (2) $\textit{Low Generalization Cost}$: it achieves sub-second training and inference, requiring only partial test inputs and no external data, whereas prior methods often take minutes or even hours. Experiments on the real-world data from multiple datasets demonstrate that our method achieves state-of-the-art quality and efficiency in tackling cross-sensor degradation. For example, training and inference of $512\times512\times8$ image within $\textit{0.2 seconds}$ and $4000\times4000\times8$ image within $\textit{3 seconds}$ at the fastest setting on a commonly used RTX 3090 GPU, which is over 100 times faster than zero-shot methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_07369 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Training and Inference within 1 Second -- Tackle Cross-Sensor Degradation of Real-World Pansharpening with Efficient Residual Feature Tailoring Xin, Tianyu Xiao, Jin-Liang Xia, Zeyu Yin, Shan Deng, Liang-Jian Computer Vision and Pattern Recognition Deep learning methods for pansharpening have advanced rapidly, yet models pretrained on data from a specific sensor often generalize poorly to data from other sensors. Existing methods to tackle such cross-sensor degradation include retraining model or zero-shot methods, but they are highly time-consuming or even need extra training data. To address these challenges, our method first performs modular decomposition on deep learning-based pansharpening models, revealing a general yet critical interface where high-dimensional fused features begin mapping to the channel space of the final image. % may need revisement A Feature Tailor is then integrated at this interface to address cross-sensor degradation at the feature level, and is trained efficiently with physics-aware unsupervised losses. Moreover, our method operates in a patch-wise manner, training on partial patches and performing parallel inference on all patches to boost efficiency. Our method offers two key advantages: (1) $\textit{Improved Generalization Ability}$: it significantly enhance performance in cross-sensor cases. (2) $\textit{Low Generalization Cost}$: it achieves sub-second training and inference, requiring only partial test inputs and no external data, whereas prior methods often take minutes or even hours. Experiments on the real-world data from multiple datasets demonstrate that our method achieves state-of-the-art quality and efficiency in tackling cross-sensor degradation. For example, training and inference of $512\times512\times8$ image within $\textit{0.2 seconds}$ and $4000\times4000\times8$ image within $\textit{3 seconds}$ at the fastest setting on a commonly used RTX 3090 GPU, which is over 100 times faster than zero-shot methods. |
| title | Training and Inference within 1 Second -- Tackle Cross-Sensor Degradation of Real-World Pansharpening with Efficient Residual Feature Tailoring |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.07369 |