IncepDeHazeGAN: Novel Satellite Image Dehazing

TL;DR

IncepDeHazeGAN is a novel GAN-based model that employs Inception blocks and multi-layer feature fusion to improve single-image dehazing, achieving state-of-the-art results in remote sensing data.

Contribution

The paper introduces a new GAN architecture with multi-scale feature extraction and fusion, enhanced by Grad-CAM explainability for satellite image dehazing.

Findings

Achieves state-of-the-art dehazing performance on multiple datasets.

Utilizes Grad-CAM for interpretability of the dehazing process.

Employs multi-layer feature fusion for efficient feature reuse.

Abstract

Dehazing is a technique in computer vision for enhancing the visual quality of images captured in cloudy or foggy conditions. Dehazing helps to recover clear, high-quality images from haze-affected remote sensing data. In this study, we introduce IncepDeHazeGAN, a novel Generative Adversarial Network (GAN) involving Inception block and multi-layer feature fusion for the task of single-image dehazing. Utilizing the Inception block allows for multi-scale feature extraction. On the other hand, the multi-layer feature fusion design achieves efficient reuse of features as the features extracted at different convolution layers are fused several times. Grad-CAM XAI technique has been applied to our network, highlighting the regions focused on by the network for dehazing and its adaptation to different haze conditions. Experiments demonstrate that our network achieves state-of-the-art results in several datasets.