Affordable Access

deepdyve-link
Publisher Website

Semi-Supervised Image Dehazing.

Authors
  • Li, Lerenhan
  • Dong, Yunlong
  • Ren, Wenqi
  • Pan, Jinshan
  • Gao, Changxin
  • Sang, Nong
  • Yang, Ming-Hsuan
Type
Published Article
Journal
IEEE Transactions on Image Processing
Publisher
Institute of Electrical and Electronics Engineers
Publication Date
Nov 15, 2019
Identifiers
DOI: 10.1109/TIP.2019.2952690
PMID: 31751272
Source
Medline
Language
English
License
Unknown

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.

Report this publication

Statistics

Seen <100 times