Stereo Refinement Dehazing Network

Jing Nie, Yanwei Pang, Jin Xie, Jing Pan, Jungong Han

Research output: Contribution to journalArticlepeer-review

10 Citations (Scopus)
143 Downloads (Pure)


The performance of stereo vision tasks degrades when haze exists in the input stereo image pair. Independently applying single image dehazing algorithm on left and right images is not optimal. To overcome the problem, we propose an effective framework, called SRDNet, for simultaneously dehazing stereo images. The main idea of SRDNet is to make full use of the stereo information from cross views improving dehazing performance. It does not explicitly employ the disparity estimation and the correlation matrix. SRDNet comprises two parts: a weight-sharing coarse dehazing network (WSCDN) and a guided separated refinement network (GSRN). The WSCDN is utilized to predict a coarse dehazed image pair. Then the GSRN is introduced to predict the residues for different views by extracting the fused information of cross views and separating the features of different views with a guided channel and spatial refinement module. The residues are added to the coarse dehazed pair so as to make refinement and remove the remained haze. Experimental results demonstrate that our proposed SRDNet surpasses previous image dehazing methods by a significant margin both quantitatively and qualitatively. Moreover, our SRDNet could be a preprocessing step of the stereo-based 3D object detection and boosts the 3D detection accuracy in hazy scenes.

Original languageEnglish
Pages (from-to)3334-3345
Number of pages12
JournalIEEE Transactions on Circuits and Systems for Video Technology
Issue number6
Early online date18 Aug 2021
Publication statusPublished - 06 Jun 2022


  • Atmospheric modeling
  • channel and spatial refinement
  • Computational modeling
  • deep learning
  • Feature extraction
  • Image restoration
  • Stereo image dehazing
  • Stereo vision
  • Task analysis
  • Three-dimensional displays


Dive into the research topics of 'Stereo Refinement Dehazing Network'. Together they form a unique fingerprint.

Cite this