Domain Adaptation for Image Dehazing

TL;DR

This paper introduces a domain adaptation framework for image dehazing that combines image translation and dehazing networks, improving generalization from synthetic to real hazy images through end-to-end training.

Contribution

It proposes a novel domain adaptation paradigm with an image translation module and two dehazing networks trained jointly for better real-world performance.

Findings

Outperforms state-of-the-art dehazing methods on synthetic and real images.

Effectively bridges the domain gap between synthetic and real hazy images.

Enhances dehazing quality through end-to-end training with domain adaptation techniques.

Abstract

Image dehazing using learning-based methods has achieved state-of-the-art performance in recent years. However, most existing methods train a dehazing model on synthetic hazy images, which are less able to generalize well to real hazy images due to domain shift. To address this issue, we propose a domain adaptation paradigm, which consists of an image translation module and two image dehazing modules. Specifically, we first apply a bidirectional translation network to bridge the gap between the synthetic and real domains by translating images from one domain to another. And then, we use images before and after translation to train the proposed two image dehazing networks with a consistency constraint. In this phase, we incorporate the real hazy image into the dehazing training via exploiting the properties of the clear image (e.g., dark channel prior and image gradient smoothing) to further improve the domain adaptivity. By training image translation and dehazing network in an end-to-end manner, we can obtain better effects of both image translation and dehazing. Experimental results on both synthetic and real-world images demonstrate that our model performs favorably against the state-of-the-art dehazing algorithms.