DW-GAN: A Discrete Wavelet Transform GAN for NonHomogeneous Dehazing

TL;DR

This paper introduces DW-GAN, a novel non-homogeneous image dehazing method using discrete wavelet transform and pre-trained Res2Net, which effectively preserves details and improves generalization over existing CNN-based approaches.

Contribution

The paper proposes a two-branch GAN incorporating wavelet transform and pre-trained Res2Net to enhance non-homogeneous dehazing performance and robustness.

Findings

Outperforms state-of-the-art methods quantitatively.

Preserves high-frequency details effectively.

Reduces artifacts with patch-based discriminator.

Abstract

Hazy images are often subject to color distortion, blurring, and other visible quality degradation. Some existing CNN-based methods have great performance on removing homogeneous haze, but they are not robust in non-homogeneous case. The reasons are mainly in two folds. Firstly, due to the complicated haze distribution, texture details are easy to be lost during the dehazing process. Secondly, since the training pairs are hard to be collected, training on limited data can easily lead to over-fitting problem. To tackle these two issues, we introduce a novel dehazing network using 2D discrete wavelet transform, namely DW-GAN. Specifically, we propose a two-branch network to deal with the aforementioned problems. By utilizing wavelet transform in DWT branch, our proposed method can retain more high-frequency knowledge in feature maps. In order to prevent over-fitting, ImageNet pre-trained Res2Net is adopted in the knowledge adaptation branch. Owing to the robust feature representations of ImageNet pre-training, the generalization ability of our network is improved dramatically. Finally, a patch-based discriminator is used to reduce artifacts of the restored images. Extensive experimental results demonstrate that the proposed method outperforms the state-of-the-arts quantitatively and qualitatively.