首页> 外文会议>AAAI Conference on Artificial Intelligence >FD-GAN: Generative Adversarial Networks with Fusion-Discriminator for Single Image Dehazing
【24h】

FD-GAN: Generative Adversarial Networks with Fusion-Discriminator for Single Image Dehazing

机译:FD-GaN:具有融合鉴别器的生成对抗网络,用于单幅图像脱水

获取原文

摘要

Recently, convolutional neural networks (CNNs) have achieved great improvements in single image dehazing and attained much attention in research. Most existing learning-based dehazing methods are not fully end-to-end, which still follow the traditional dehazing procedure: first estimate the medium transmission and the atmospheric light, then recover the haze-free image based on the atmospheric scattering model. However, in practice, due to lack of priors and constraints, it is hard to precisely estimate these intermediate parameters. Inaccurate estimation further degrades the performance of dehazing, resulting in artifacts, color distortion and insufficient haze removal. To address this, we propose a fully end-to-end Generative Adversarial Networks with Fusion-discriminator (FD-GAN) for image dehazing. With the proposed Fusion-discriminator which takes frequency information as additional priors, our model can generator more natural and realistic dehazed images with less color distortion and fewer artifacts. Moreover, we synthesize a large-scale training dataset including various indoor and outdoor hazy images to boost the performance and we reveal that for learning-based dehazing methods, the performance is strictly influenced by the training data. Experiments have shown that our method reaches state-of-the-art performance on both public synthetic datasets and real-world images with more visually pleasing dehazed results.
机译:最近,卷积神经网络(CNNS)在单一图像脱水中取得了巨大的改进,并在研究中达到了很多关注。大多数现有的基于学习的去吸收方法并不完全结束,这仍然遵循传统的去析过程:首先估计中等传输和大气光,然后基于大气散射模型恢复无雾图像。然而,在实践中,由于缺乏前沿和约束,很难精确估计这些中间参数。不准确的估计进一步降低了脱落的性能,导致伪影,颜色变形和雾度不足去除。为了解决这个问题,我们提出了一个完全端到端的生成对冲网络,用于融合鉴别器(FD-GAN),用于图像脱水。通过提出的融合鉴别者,将频率信息作为额外的前导者,我们的模型可以产生更自然和现实的去隐藏图像,具有较少的颜色失真和更少的伪像。此外,我们综合了一个大型训练数据集,包括各种室内和户外朦胧图像来提高性能,我们揭示了一种基于学习的脱水方法,性能受到训练数据的严格影响。实验表明,我们的方法在公共合成数据集和现实世界形象中达到最先进的性能,并具有更明显的令人愉悦的脱离结果。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号