Unsupervised Conditional Disentangle Network for Image Dehazing

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Image dehazing aims to restore the blurry image information caused by the ambiguities of unknown scene radiance and transmission. Instead of using paired images or depth information, we propose an Unsupervised Conditional Disentangle Network (UCDN) using unpaired dataset. Our approach enforces the constraint by introducing physical-based disentanglement. Unlike other unsupervised dehazing models, our approach adapts the multi-concentration of fog and outperforms on the dataset with different concentrations. Extensive experiments on synthesized dataset demonstrate that our approach can surpass state-of-the-arts. Meanwhile, through benchmarking on our collected natural hazy dataset, our approach can generate more perceptually appealing dehazing results.

Original languageEnglish
Title of host publication2020 IEEE International Conference on Image Processing, ICIP 2020 - Proceedings
PublisherIEEE Computer Society
Pages963-967
Number of pages5
ISBN (Electronic)9781728163956
DOIs
StatePublished - Oct 2020
Event2020 IEEE International Conference on Image Processing, ICIP 2020 - Virtual, Abu Dhabi, United Arab Emirates
Duration: 25 Sep 202028 Sep 2020

Publication series

NameProceedings - International Conference on Image Processing, ICIP
Volume2020-October
ISSN (Print)1522-4880

Conference

Conference2020 IEEE International Conference on Image Processing, ICIP 2020
Country/TerritoryUnited Arab Emirates
CityVirtual, Abu Dhabi
Period25/09/2028/09/20

Keywords

  • GAN
  • image enhancing
  • natural hazy dataset
  • single image dehazing
  • unsupervised

Fingerprint

Dive into the research topics of 'Unsupervised Conditional Disentangle Network for Image Dehazing'. Together they form a unique fingerprint.

Cite this