RefineDNet: A Weakly Supervised Refinement Framework for Single Image Dehazing
RefineDNet: A Weakly Supervised Refinement Framework for Single Image Dehazing
复制标题
DOI：
10.1109/tip.2021.3060873
复制
发表时间：
2021-03
影响因子：
10.6
通讯作者：
Shiyu Zhao;Lin Zhang;Ying Shen;Yicong Zhou
中科院分区：
文献类型：
--
作者：
Shiyu Zhao;Lin Zhang;Ying Shen;Yicong Zhou
无雾图像是许多视觉系统和算法的先决条件，因此单幅图像去雾在计算机视觉中至关重要。在这一领域，基于先验的方法已经取得了初步成功。然而，它们经常在输出中引入令人讨厌的工件，因为它们的先验很难适应所有情况。相比之下，基于学习的方法可以产生更自然的结果。然而，由于缺乏与训练样本相同场景的成对的有雾且清晰的户外图像，其去雾能力有限。在这项工作中，我们试图通过将去雾任务分为两个子任务，即可见性恢复和真实感改善，来融合基于先验和基于学习的方法的优点。具体来说，我们提出了一个两阶段弱监督脱雾框架，RefineDNet。在第一阶段，RefineDNet在恢复可见性之前采用暗通道。然后，在第二阶段，对第一阶段的初步去雾结果进行细化，通过对未配对的雾蒙蒙和清晰图像进行对抗性学习，提高真实感。为了获得更合格的结果，我们还提出了一种有效的感知融合策略来混合不同的除雾输出。大量的实验证实，采用感知融合的RefineDNet具有出色的去雾能力，也能产生视觉上令人愉悦的效果。即使使用基本的骨干网络，RefineDNet也可以在室内和室外数据集上优于监督除雾方法以及其他最先进的方法。为了使我们的结果可重复，相关代码和数据可在https://github.com/xiaofeng94/RefineDNet-for-dehazing上获得。
Haze-free images are the prerequisites of many vision systems and algorithms, and thus single image dehazing is of paramount importance in computer vision. In this field, prior-based methods have achieved initial success. However, they often introduce annoying artifacts to outputs because their priors can hardly fit all situations. By contrast, learning-based methods can generate more natural results. Nonetheless, due to the lack of paired foggy and clear outdoor images of the same scenes as training samples, their haze removal abilities are limited. In this work, we attempt to merge the merits of prior-based and learning-based approaches by dividing the dehazing task into two sub-tasks, i.e., visibility restoration and realness improvement. Specifically, we propose a two-stage weakly supervised dehazing framework, RefineDNet. In the first stage, RefineDNet adopts the dark channel prior to restore visibility. Then, in the second stage, it refines preliminary dehazing results of the first stage to improve realness via adversarial learning with unpaired foggy and clear images. To get more qualified results, we also propose an effective perceptual fusion strategy to blend different dehazing outputs. Extensive experiments corroborate that RefineDNet with the perceptual fusion has an outstanding haze removal capability and can also produce visually pleasing results. Even implemented with basic backbone networks, RefineDNet can outperform supervised dehazing approaches as well as other state-of-the-art methods on indoor and outdoor datasets. To make our results reproducible, relevant code and data are available at https://github.com/xiaofeng94/RefineDNet-for-dehazing.