Dehazing Remote Sensing and UAV Imagery: A Review of Deep Learning, Prior-based, and Hybrid Approaches

TL;DR

This review comprehensively discusses recent deep learning, prior-based, and hybrid dehazing methods applied to remote sensing and UAV imagery, highlighting challenges like dataset scarcity and evaluation metrics.

Contribution

It provides the first extensive overview of dehazing techniques specifically tailored for remote sensing and UAV datasets, including recent advances and future directions.

Findings

Deep learning approaches dominate recent dehazing research.

Lack of large-scale remote sensing datasets hampers progress.

Evaluation metrics need standardization for better comparison.

Abstract

High-quality images are crucial in remote sensing and UAV applications, but atmospheric haze can severely degrade image quality, making image dehazing a critical research area. Since the introduction of deep convolutional neural networks, numerous approaches have been proposed, and even more have emerged with the development of vision transformers and contrastive/few-shot learning. Simultaneously, papers describing dehazing architectures applicable to various Remote Sensing (RS) domains are also being published. This review goes beyond the traditional focus on benchmarked haze datasets, as we also explore the application of dehazing techniques to remote sensing and UAV datasets, providing a comprehensive overview of both deep learning and prior-based approaches in these domains. We identify key challenges, including the lack of large-scale RS datasets and the need for more robust evaluation metrics, and outline potential solutions and future research directions to address them. This review is the first, to our knowledge, to provide comprehensive discussions on both existing and very recent dehazing approaches (as of 2024) on benchmarked and RS datasets, including UAV-based imagery.