PMAA: A Progressive Multi-scale Attention Autoencoder Model for High-performance Cloud Removal from Multi-temporal Satellite Imagery
This addresses cloud cover issues in remote sensing for applications like environmental monitoring, offering a lightweight solution suitable for edge deployment, though it is incremental as it builds on existing deep learning methods.
The paper tackles cloud removal in satellite imagery by proposing the Progressive Multi-scale Attention Autoencoder (PMAA), which outperforms the previous state-of-the-art model CTGAN on benchmark datasets while using only 0.5% of parameters and 14.6% of computational complexity.
Satellite imagery analysis plays a pivotal role in remote sensing; however, information loss due to cloud cover significantly impedes its application. Although existing deep cloud removal models have achieved notable outcomes, they scarcely consider contextual information. This study introduces a high-performance cloud removal architecture, termed Progressive Multi-scale Attention Autoencoder (PMAA), which concurrently harnesses global and local information to construct robust contextual dependencies using a novel Multi-scale Attention Module (MAM) and a novel Local Interaction Module (LIM). PMAA establishes long-range dependencies of multi-scale features using MAM and modulates the reconstruction of fine-grained details utilizing LIM, enabling simultaneous representation of fine- and coarse-grained features at the same level. With the help of diverse and multi-scale features, PMAA consistently outperforms the previous state-of-the-art model CTGAN on two benchmark datasets. Moreover, PMAA boasts considerable efficiency advantages, with only 0.5% and 14.6% of the parameters and computational complexity of CTGAN, respectively. These comprehensive results underscore PMAA's potential as a lightweight cloud removal network suitable for deployment on edge devices to accomplish large-scale cloud removal tasks. Our source code and pre-trained models are available at https://github.com/XavierJiezou/PMAA.