Enpowering Your Pansharpening Models with Generalizability: Unified Distribution is All You Need
This addresses the limited applicability of pansharpening models in remote sensing by improving generalizability, though it is incremental as it builds on existing methods with a novel normalization approach.
The paper tackles the problem of poor generalizability in deep learning-based pansharpening models for remote sensing, which suffer performance drops on unseen satellite data due to distributional discrepancies, and introduces UniPAN, a unified distribution strategy that normalizes data to enhance model performance across diverse sensors.
Existing deep learning-based models for remote sensing pansharpening exhibit exceptional performance on training datasets. However, due to sensor-specific characteristics and varying imaging conditions, these models suffer from substantial performance degradation when applied to unseen satellite data, lacking generalizability and thus limiting their applicability. We argue that the performance drops stem primarily from distributional discrepancies from different sources and the key to addressing this challenge lies in bridging the gap between training and testing distributions. To validate the idea and further achieve a "train once, deploy forever" capability, this paper introduces a novel and intuitive approach to enpower any pansharpening models with generalizability by employing a unified distribution strategy (UniPAN). Specifically, we construct a distribution transformation function that normalizes the pixels sampled from different sources to conform to an identical distribution. The deep models are trained on the transformed domain, and during testing on new datasets, the new data are also transformed to match the training distribution. UniPAN aims to train and test the model on a unified and consistent distribution, thereby enhancing its generalizability. Extensive experiments validate the efficacy of UniPAN, demonstrating its potential to significantly enhance the performance of deep pansharpening models across diverse satellite sensors. Codes: https://github.com/yc-cui/UniPAN.