Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Zongsheng Yue"'
Publikováno v:
Remote Sensing, Vol 10, Iss 10, p 1631 (2018)
Hyperspectral images (HSIs) are always corrupted by complicated forms of noise during the acquisition process, such as Gaussian noise, impulse noise, stripes, deadlines and so on. Specifically, different bands of the practical HSIs generally contain
Externí odkaz:
https://doaj.org/article/afc5595c15c9418590806c58923d5b51
Publikováno v:
Knowledge-Based Systems. 249:109008
Blind image deblurring is an important yet very challenging problem in low-level vision. Traditional optimization based methods generally formulate this task as a maximum-a-posteriori estimation or variational inference problem, whose performance hig
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0fee26d6e36c60c8df9397e68df0743d
https://doi.org/10.1016/j.knosys.2022.109008
https://doi.org/10.1016/j.knosys.2022.109008
Publikováno v:
CVPR
An efficient approach for handling hyperspectral image (HSI) denoising issue is to impose weights on different HSI pixels to suppress negative influence brought by noisy elements. Such weighting scheme, however, largely depends on the prior understan
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c9c9d19c20dd710d4345a801c9376867
https://doi.org/10.1109/cvpr46437.2021.00667
https://doi.org/10.1109/cvpr46437.2021.00667
Publikováno v:
CVPR
For the single image rain removal (SIRR) task, the performance of deep learning (DL)-based methods is mainly affected by the designed deraining models and training datasets. Most of current state-of-the-art focus on constructing powerful deep models
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f332890507f9e6b1398ca05f38b0987d
https://doi.org/10.1109/cvpr46437.2021.01455
https://doi.org/10.1109/cvpr46437.2021.01455
Publikováno v:
CVPR
While deep learning (DL)-based video deraining methods have achieved significant success recently, they still exist two major drawbacks. Firstly, most of them do not sufficiently model the characteristics of rain layers of rainy videos. In fact, the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8986694d7e8b566d49b68105454bc5ab
http://arxiv.org/abs/2103.07939
http://arxiv.org/abs/2103.07939
Autor:
Zongsheng Yue, Yan Tian
Publikováno v:
Advances in Social Science, Education and Humanities Research.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c72247c5112b64b1fb9a2b2212f5b6ca
https://doi.org/10.2991/assehr.k.210813.029
https://doi.org/10.2991/assehr.k.210813.029
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030586065
ECCV (10)
ECCV (10)
Real-world image noise removal is a long-standing yet very challenging task in computer vision. The success of deep neural network in denoising stimulates the research of noise generation, aiming at synthesizing more clean-noisy image pairs to facili
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c9dc7ec1e95dbb06faa8fd1174c4800b
https://doi.org/10.1007/978-3-030-58607-2_3
https://doi.org/10.1007/978-3-030-58607-2_3
Autor:
Zhuo Li, Zongsheng Yue
Publikováno v:
Proceedings of the 4th International Conference on Art Studies: Science, Experience, Education (ICASSEE 2020).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a89a27d0a1c162ad2397059b5a0d7676
https://doi.org/10.2991/assehr.k.200907.086
https://doi.org/10.2991/assehr.k.200907.086
Autor:
Zhuo Li, Zongsheng Yue
Publikováno v:
Proceedings of the 2020 Conference on Education, Language and Inter-cultural Communication (ELIC 2020).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9da1971df4ddc48132cd2dce943a8fae
https://doi.org/10.2991/assehr.k.201127.133
https://doi.org/10.2991/assehr.k.201127.133
Publikováno v:
Image and Vision Computing. 60:38-47
Graph-based semi-supervised learning (GSSL) attracts considerable attention in recent years. The performance of a general GSSL method relies on the quality of Laplacian weighted graph (LWR) composed of the similarity imposed on input examples. A key
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::05e9999985eec1cc541ce4a96b2bb981
https://doi.org/10.1016/j.imavis.2016.11.013
https://doi.org/10.1016/j.imavis.2016.11.013