Thin Cloud Removal for Remote Sensing Images Using a Physical-Model-Based CycleGAN With Unpaired Data
Thin Cloud Removal for Remote Sensing Images Using a Physical-Model-Based CycleGAN With Unpaired Data
复制标题
使用基于物理模型的 CycleGAN 和不成对数据去除遥感图像的薄云
DOI：
10.1109/lgrs.2021.3140033
复制
发表时间：
2022
影响因子：
4.8
通讯作者：
Haopeng Zhang
中科院分区：
文献类型：
--
作者：
Yue Zi;Fengying Xie;Xuedong Song;Zhiguo Jiang;Haopeng Zhang
从遥感（RS）图像中去除薄云具有挑战性。最近，基于深度学习的方法对成对图像数据进行监督训练，取得了很好的效果。然而，在实践中，真实的配对图像数据是不可用的。因此，在这封信中，我们提出了一种新的薄云去除方法，一种基于物理模型的CycleGAN (PM-CycleGAN)，它可以只使用未配对的数据进行训练。PM-CycleGAN训练过程包括正向和反向循环。前向循环首先使用三个生成器将多云图像分解为无云图像、薄云厚度图和厚度系数。然后，利用物理模型将这三个分量组合起来重建原始浑浊图像，得到周期一致性约束。后向循环首先使用物理模型将无云图像、薄云厚度图和厚度系数合成为云图像，然后使用三个生成器将其分解为原始的三个分量。与几种最先进的（SOTA）方法在云图数据集上的视觉和定量比较证明了PM-CycleGAN的优越性。
Thin cloud removal from remote sensing (RS) images is challenging. Recently, deep-learning-based methods have achieved excellent results using supervised training on paired image data. However, in practice, real paired image data are unavailable. Therefore, in this letter, we propose a novel thin cloud removal method, a physical-model-based CycleGAN (PM-CycleGAN), which can be trained using only unpaired data. The PM-CycleGAN training process comprises forward and backward loops. The forward loop first decomposes a cloudy image into a cloud-free image, thin cloud thickness map, and thickness coefficient using three generators. Then, it combines these three components using a physical model to reconstruct the original cloudy image to obtain the cycle consistency constraint. The backward loop first uses the physical model to synthesize a cloud-free image, thin cloud thickness map, and thickness coefficient into a cloudy image, which are then decomposed into the original three components using the three generators. Visual and quantitative comparisons against several state-of-the-art (SOTA) methods on a cloudy image dataset demonstrated the superiority of PM-CycleGAN.