AI Article Synopsis

  • The study introduces a semi-supervised learning algorithm designed to improve single image dehazing using a deep Convolutional Neural Network (CNN) with both supervised and unsupervised branches.
  • The supervised branch employs various loss functions (mean squared, perceptual, and adversarial) to guide the learning, while the unsupervised branch leverages characteristics of clean images for additional constraints.
  • The algorithm has been trained on both synthetic and real-world image datasets, demonstrating strong performance compared to existing dehazing methods, indicating its generalizability beyond just synthetic data.

Article Abstract

We present an effective semi-supervised learning algorithm for single image dehazing. The proposed algorithm applies a deep Convolutional Neural Network (CNN) containing a supervised learning branch and an unsupervised learning branch. In the supervised branch, the deep neural network is constrained by the supervised loss functions, which are mean squared, perceptual, and adversarial losses. In the unsupervised branch, we exploit the properties of clean images via sparsity of dark channel and gradient priors to constrain the network. We train the proposed network on both the synthetic data and real-world images in an end-to-end manner. Our analysis shows that the proposed semi-supervised learning algorithm is not limited to synthetic training datasets and can be generalized well to real-world images. Extensive experimental results demonstrate that the proposed algorithm performs favorably against the state-of-the-art single image dehazing algorithms on both benchmark datasets and real-world images.

Download full-text PDF

Source
http://dx.doi.org/10.1109/TIP.2019.2952690DOI Listing

Publication Analysis

Top Keywords

image dehazing
12
real-world images
12
semi-supervised learning
8
learning algorithm
8
single image
8
proposed algorithm
8
neural network
8
learning branch
8
semi-supervised image
4
dehazing effective
4

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!