Multi-Head Linear Attention Generative Adversarial Network for Thin Cloud Removal

TL;DR

This paper introduces MLA-GAN, a novel generative adversarial network utilizing multi-head linear attention, designed to effectively remove thin clouds from remote sensing images by leveraging pixel dependencies.

Contribution

The paper proposes a new GAN architecture with multi-head linear attention for improved thin cloud removal, outperforming existing deep learning methods.

Findings

MLA-GAN achieves superior performance on RICE datasets.

The model effectively preserves surface details in cloud-affected areas.

Experimental results show dominant advantages over benchmarks.

Abstract

In remote sensing images, the existence of the thin cloud is an inevitable and ubiquitous phenomenon that crucially reduces the quality of imageries and limits the scenarios of application. Therefore, thin cloud removal is an indispensable procedure to enhance the utilization of remote sensing images. Generally, even though contaminated by thin clouds, the pixels still retain more or less surface information. Hence, different from thick cloud removal, thin cloud removal algorithms normally concentrate on inhibiting the cloud influence rather than substituting the cloud-contaminated pixels. Meanwhile, considering the surface features obscured by the cloud are usually similar to adjacent areas, the dependency between each pixel of the input is useful to reconstruct contaminated areas. In this paper, to make full use of the dependencies between pixels of the image, we propose a Multi-Head Linear Attention Generative Adversarial Network (MLAGAN) for Thin Cloud Removal. The MLA-GAN is based on the encoding-decoding framework consisting of multiple attention-based layers and deconvolutional layers. Compared with six deep learning-based thin cloud removal benchmarks, the experimental results on the RICE1 and RICE2 datasets demonstrate that the proposed framework MLA-GAN has dominant advantages in thin cloud removal.