# Single Image Haze Removal Using Conditional Wasserstein Generative Adversarial Networks

## TL;DR

This paper introduces a novel end-to-end Wasserstein GAN approach for single image haze removal that outperforms existing methods by learning the conditional distribution of clear images from hazy inputs.

## Contribution

The paper proposes a data-adaptive, end-to-end Wasserstein GAN with texture and L1 losses for haze removal, eliminating the need for priors or multiple images.

## Key findings

- Outperforms current state-of-the-art haze removal methods
- Uses a Wasserstein loss with gradient penalty for stable training
- Incorporates texture and L1 losses to enhance image quality

## Abstract

We present a method to restore a clear image from a haze-affected image using a Wasserstein generative adversarial network. As the problem is ill-conditioned, previous methods have required a prior on natural images or multiple images of the same scene. We train a generative adversarial network to learn the probability distribution of clear images conditioned on the haze-affected images using the Wasserstein loss function, using a gradient penalty to enforce the Lipschitz constraint. The method is data-adaptive, end-to-end, and requires no further processing or tuning of parameters. We also incorporate the use of a texture-based loss metric and the L1 loss to improve results, and show that our results are better than the current state-of-the-art.