# Training and Inference within 1 Second -- Tackle Cross-Sensor Degradation of Real-World Pansharpening with Efficient Residual Feature Tailoring

arXiv: https://arxiv.org/abs/2508.07369 · HTML: https://mlsanity.com/paper/2508.07369/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 37 references that are in the map.
- First posted on arXiv 10 Aug 2025.

## Builds on (most cited first, 7 of 7)

- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Domain Generalization via Model-Agnostic Learning of Semantic Features](https://mlsanity.com/paper/1910.13580/) (2019)
- [Pansharpening via Detail Injection Based Convolutional Neural Networks](https://mlsanity.com/paper/1806.08898/) (2018)
- [U2Net: A General Framework with Spatial-Spectral-Integrated Double U-Net for Image Fusion](https://mlsanity.com/paper/2212.06466/) (2022)
- [Wavelet-Assisted Multi-Frequency Attention Network for Pansharpening](https://mlsanity.com/paper/2502.04903/) (2025)
- [MMAIF: Multi-task and Multi-degradation All-in-One for Image Fusion with Language Guidance](https://mlsanity.com/paper/2503.14944/) (2025)

## Built on by (most cited first, 1 of 1)

- [DMAConv: Dual Mask-Adaptive Convolution for Remote Sensing Pansharpening](https://mlsanity.com/paper/2512.08331/) (2025)

## Abstract (arXiv)

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) textitImproved Generalization Ability: it significantly enhance performance in cross-sensor cases. (2) textitLow 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 512×512×8 image within textit0.2 seconds and 4000×4000×8 image within textit3 seconds at the fastest setting on a commonly used RTX 3090 GPU, which is over 100 times faster than zero-shot methods.