The Library
BidNet : Binocular Image Dehazing without explicit disparity estimation
Tools
Pang, Yanwei, Nie, Jing, Xie, Jin, Han, Jungong and Li, Xuelong (2020) BidNet : Binocular Image Dehazing without explicit disparity estimation. In: IEEE Conference on Computer Vision and Pattern Recognition 2020, Seattle, Washington, 14-19 Jun 2020. Published in: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) ISBN 9781728171692. doi:10.1109/CVPR42600.2020.00597 ISSN 2575-7075.
|
PDF
WRAP-BidNet-binocular-dehazing-disparity-Han-2020.pdf - Accepted Version - Requires a PDF viewer. Download (8Mb) | Preview |
Official URL: https://doi.org/10.1109/CVPR42600.2020.00597
Abstract
Heavy haze results in severe image degradation and thus hampers the performance of visual perception, object detection, etc. On the assumption that dehazed binocular images are superior to the hazy ones for stereo vision tasks such as 3D object detection and according to the fact that image haze is a function of depth, this paper proposes a Binocular image dehazing Network (BidNet) aiming at dehazing both the left and right images of binocular images within the deep learning framework. Existing binocular dehazing methods rely on simultaneously dehazing and estimating disparity, whereas BidNet does not need to explicitly perform time-consuming and well-known challenging disparity estimation. Note that a small error in disparity gives rise to a large variation in depth and in estimation of haze-free image. The relationship and correlation between binocular images are explored and encoded by the proposed Stereo Transformation Module (STM). Jointly dehazing binocular image pairs is mutually beneficial, which is better than only dehazing left images. We extend the Foggy Cityscapes dataset to a Stereo Foggy Cityscapes dataset with binocular foggy image pairs. Experimental results demonstrate that BidNet significantly outperforms state-of-the-art dehazing methods in both subjective and objective assessments.
Item Type: | Conference Item (Paper) | ||||||
---|---|---|---|---|---|---|---|
Alternative Title: | |||||||
Divisions: | Faculty of Science, Engineering and Medicine > Engineering > WMG (Formerly the Warwick Manufacturing Group) | ||||||
Journal or Publication Title: | 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) | ||||||
Publisher: | IEEE | ||||||
ISBN: | 9781728171692 | ||||||
ISSN: | 2575-7075 | ||||||
Official Date: | 5 August 2020 | ||||||
Dates: |
|
||||||
DOI: | 10.1109/CVPR42600.2020.00597 | ||||||
Status: | Peer Reviewed | ||||||
Publication Status: | Published | ||||||
Reuse Statement (publisher, data, author rights): | © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | ||||||
Access rights to Published version: | Restricted or Subscription Access | ||||||
Date of first compliant deposit: | 8 April 2020 | ||||||
Date of first compliant Open Access: | 22 December 2020 | ||||||
Conference Paper Type: | Paper | ||||||
Title of Event: | IEEE Conference on Computer Vision and Pattern Recognition 2020 | ||||||
Type of Event: | Conference | ||||||
Location of Event: | Seattle, Washington | ||||||
Date(s) of Event: | 14-19 Jun 2020 | ||||||
Related URLs: |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |
Downloads
Downloads per month over past year