计算机科学
人工智能
图像(数学)
推论
计算机视觉
图层(电子)
深度学习
传输(电信)
深层神经网络
基本事实
人工神经网络
模式识别(心理学)
电信
有机化学
化学
作者
Boyun Li,Yuanbiao Gou,Zitao Liu,Hongyuan Zhu,Joey Tianyi Zhou,Xi Peng
出处
期刊:IEEE transactions on image processing
[Institute of Electrical and Electronics Engineers]
日期:2020-01-01
卷期号:29: 8457-8466
被引量:79
标识
DOI:10.1109/tip.2020.3016134
摘要
In this paper, we study two less-touched challenging problems in single image dehazing neural networks, namely, how to remove haze from a given image in an unsupervised and zeroshot manner. To the ends, we propose a novel method based on the idea of layer disentanglement by viewing a hazy image as the entanglement of several "simpler" layers, i.e., a hazy-free image layer, transmission map layer, and atmospheric light layer. The major advantages of the proposed ZID are two-fold. First, it is an unsupervised method that does not use any clean images including hazy-clean pairs as the ground-truth. Second, ZID is a "zero-shot" method, which just uses the observed single hazy image to perform learning and inference. In other words, it does not follow the conventional paradigm of training deep model on a large scale dataset. These two advantages enable our method to avoid the labor-intensive data collection and the domain shift issue of using the synthetic hazy images to address the real-world images. Extensive comparisons show the promising performance of our method compared with 15 approaches in the qualitative and quantitive evaluations. The source code could be found at www.pengxi.me.
科研通智能强力驱动
Strongly Powered by AbleSci AI