A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Filters
DW-GAN: A Discrete Wavelet Transform GAN for NonHomogeneous Dehazing
[article]
2021
arXiv
pre-print
Preserved Fulltext
Other Versions
Firstly, due to the complicated haze distribution, texture details are easy to be lost during the dehazing process. ...
To tackle these two issues, we introduce a novel dehazing network using 2D discrete wavelet transform, namely DW-GAN. ...
TDN is the winner method in NTIRE 2020 NonHomogeneous Dehazing Challenge. Quantitative Results Comparison. The experiment results are shown in Table. 2. ...
arXiv:2104.08911v2
fatcat:7cnprpthpvgjbljrur2ycrml2i
Table of Contents
2021
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Brown (York University) NTIRE 2021 NonHomogeneous Dehazing Challenge Report 627 Codruta O. ...
Bhat (ETH Zurich), Martin Danelljan (ETH Zurich), and Radu
Timofte (ETH Zurich)
647
Ren Yang (NTIRE 2021 challenge) and Radu Timofte (NTIRE 2021
challenge)
Single Image Dehazing Using Bounded Channel ...
doi:10.1109/cvprw53098.2021.00004
fatcat:yh3zw4afzneeza6jrd6377fd3y
NTIRE 2021 Multi-modal Aerial View Object Classification Challenge
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2107.01189v1 fatcat:eqncgg7e3jfbljcuf4ib4zflriOther Versions
In this paper, we introduce the first Challenge on Multi-modal Aerial View Object Classification (MAVOC) in conjunction with the NTIRE 2021 workshop at CVPR. ...
Our challenge results show significant improvement of more than 15% accuracy from our current baselines for each track of the competition ...
This challenge is one of the NTIRE 2021 associated challenges: nonhomogeneous dehazing [4] , defocus deblurring using dual-pixel [3], depth guided image relighting [7] , image deblurring [24] , multi-modal ...
arXiv:2107.01189v3
fatcat:td5roq6nh5bkdh4m4suc2a4ruq
DAMix: A Density-Aware Mixup Augmentation for Single Image Dehazing under Domain Shift
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Deep learning-based methods have achieved considerable success on single image dehazing in recent years. ...
These datasets were introduced in the NTIRE challenge [1, 4, 6] . Since the haze in these datasets is produced by professional haze machines, they are more challenging than synthetic datasets. ...
By training with translated samples, the dehazing network can achieve better results on the real domain. [25] employs Copy-Blend augmentation [24] to simulate nonhomogeneous haze distributions. ...
arXiv:2109.12544v2
fatcat:pdu64gwpbfdireulv7r5wmzibq
NTIRE 2021 Challenge on Perceptual Image Quality Assessment
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
This paper reports on the NTIRE 2021 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at CVPR ...
2021. ...
Acknowledgements We thank the NTIRE 2021 sponsors: Huawei, Facebook Reality Labs, Wright Brothers Institute, MediaTek, OPPO and ETH Zurich (Computer Vision Lab). ...
arXiv:2105.03072v3
fatcat:mf4q3hvz4jbepgyhkzg7wbylqq
NTIRE 2021 Depth Guided Image Relighting Challenge
2021
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
In this paper, we review the NTIRE 2021 depth guided image relighting challenge. We rely on the VIDIT dataset for each of our two challenge tracks, including depth information. ...
In the second track, the any-to-any relighting challenge, the objective is to transform the illumination settings of the input image to match those of another guide image, similar to style transfer. ...
Acknowledgements We thank the NTIRE 2021 sponsors: Huawei, Facebook Reality Labs, Wright Brothers Institute, MediaTek, OPPO and ETH Zurich (Computer Vision Lab). ...
doi:10.1109/cvprw53098.2021.00069
fatcat:mihljetrtnggdbtohljudl5ioq
NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2104.10781v3 fatcat:eqflew3thvgypeyld3utfjuatiOther Versions
This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with a focus on the proposed methods and results. ...
In this challenge, the new Large-scale Diverse Video (LDV) dataset is employed. The challenge has three tracks. ...
Acknowledgments We thank the NTIRE 2021 sponsors: Huawei, Facebook Reality Labs, Wright Brothers Institute, MediaTek, OPPO and ETH Zurich (Computer Vision Lab). ...
arXiv:2104.10781v5
fatcat:v7q6rfewwbdbhfe7lj2i4u2gxa