Unsupervised single image dehazing with generative adversarial network
Open Access
- 17 February 2022
- journal article
- research article
- Published by Springer Nature in Multimedia Systems
- Vol. 29 (5) , 2923-2933
Abstract
Most recent learning algorithms for single image dehazing are designed to train with paired hazy and corresponding ground truth images, typically synthesized images. Real paired datasets can help to improve performance, but are tough to acquire. This paper proposes an unsupervised dehazing algorithm based on GAN to alleviate this issue. An end-to-end network based on GAN architecture is established and fed with unpaired clean and hazy images, signifying that the estimation of atmospheric light and transmission is not required. The proposed network consists of three parts: a generator, a global test discriminator, and a local context discriminator. Moreover, a dark channel prior based attention mechanism is applied to handle inconsistency haze. We conduct experiments on RESIDE datasets. Extensive experiments demonstrated the effectiveness of the proposed approach which outperformed previous state-of-the-art unsupervised methods by a large margin.Keywords
This publication has 33 references indexed in Scilit:
- SSD: Single Shot MultiBox Detector2016
- Single Image Dehazing via Multi-scale Convolutional Neural Networks2016
- Perceptual Losses for Real-Time Style Transfer and Super-Resolution2016
- Night-time dehazing by fusion2016
- DehazeNet: An End-to-End System for Single Image Haze RemovalIEEE Transactions on Image Processing, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- A Fast Single Image Haze Removal Algorithm Using Color Attenuation PriorIEEE Transactions on Image Processing, 2015
- Fully convolutional networks for semantic segmentation2015
- A Fast Semi-inverse Approach to Detect and Remove the Haze from a Single Image2011
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004