Results 91 to 100 of about 3,779 (211)

Progressive Update Guided Interdependent Networks for Single Image Dehazing [PDF]

, 2023
Images with haze of different varieties often pose a significant challenge to dehazing. Therefore, guidance by estimates of haze parameters related to the variety would be beneficial, and their progressive update jointly with haze reduction will allow ...
Kar, Aupendu, Biswas, Prabir Kumar, Dhara, Sobhan Kanti, Sen, Debashis   +3 more
core  

Deep Retinex Network for Single Image Dehazing

, 2021
In this paper, we propose a retinex-based decomposition model for a hazy image and a novel end-to-end image dehazing network. In the model, the illumination of the hazy image is decomposed into natural illumination for the haze-free image and residual ...
Wang, Guolin, Tang, Yandong, Wu, Chengdong, Tian, Jiandong, Li, Pengyue   +4 more
core   +1 more source

Adaptive haze pixel intensity perception transformer structure for image dehazing networks

Scientific Reports
In the realm of deep learning-based networks for dehazing using paired clean-hazy image datasets to address complex real-world haze scenarios in daytime environments and cross-dataset challenges remains a significant concern due to algorithmic ...
Jing Wu, Zhewei Liu, Feng Huang, Rong Luo   +3 more
doaj   +1 more source

Image dehazing algorithm based on light-value weighted allocation and multi-layer restricted perception

Scientific Reports
In image dehazing, the dehazing performance in bright regions and the model’s robustness to noise are critical evaluation criteria. However, existing dehazing models often suffer from distortions in the bright areas and exhibit weak noise resistance.
Dongyang Shi, Sheng Huang, Wei Zhao
doaj   +1 more source

NTIRE 2020 Challenge on NonHomogeneous Dehazing

, 2020
This paper reviews the NTIRE 2020 Challenge on Non-Homogeneous Dehazing of images (restoration of rich details in hazy image). We focus on the proposed solutions and their results evaluated on NH-Haze, a novel dataset consisting of 55 pairs of real haze ...
Ziling Huang, Yu, Zhe, Ouyang, Bing, Chang-Hong Lin, Bangyong Sun, Raghunath, Navaneeth, Aryan Mehra, Chung-En Sun, Sun, Chung-En, Huang, Ziling, Yuan Xie, Chen, Peng-Wen, Xuan Zhao, Estrada, Dennis, Park, Jongmin, Deng, Qili, Narang, Pratik, Chen, Siyi, Dennis Estrada, Tsung-Nan Lin, Chao, Ju-Chin, Zhan-Han Wang, Yu-Bang Chang, Wang, Meiqi, Lin, Chang-Hong, Tzu-Yi Liao, Codruta O. Ancuti, Vishal Monga, Dutta, Saikat, Yanyun Qu, Jing Liu, Sun, Bangyong, Zhou, Hongyu, Lee, David, Venkateswararao Cherukuri, Dong, Yu, Mingzhao Yu, Zhe Yu, Yang, Tsung-Shan, Chang, Yu-Bang, Saikat Dutta, Chuang, Shiue-Yuan, Tianqi Su, Sourya Dipta Das, Ancuti, Cosmin, Hsu, Po-Min, Tiantong Guo, Haiyan Wu, Florin-Alexandru Vasluianu, Pei-Yuan Wu, Kareem Metwaly, Jongmin Park, Meiqi Wang, Wu, Haiyan, Whannou de Dravo, Vincent, David Lee, Cosmin Ancuti, Kim, Munchurl, Jeonghyeok Do, Wu, Pei-Yuan, Mehra, Aryan, Hongyu Zhou, Xuelu Li, Cherukuri, Venkateswararao, Qili Deng, Radu Timofte, Lizhuang Ma, Navaneeth Raghunath, Wang, Zhan-Han, Yu Dong, Pratik Narang, Chang, Jerome, Jerome Chang, Munchurl Kim, Liu, Jing, Siyi Chen, Monga, Vishal, Ancuti, Codruta O, Timofte, Radu, Li, Xuelu, Lin, Tsung-Nan, Po-Min Hsu, Guo, Tiantong, Ju-Chin Chao, Do, Jeonghyeok, Yu, Mingzhao, Zhao, Xuan, Kong, Xiangzhen, Vasluianu, Florin-Alexandru, Mandal, Murari, Tsung-Shan Yang, Su, Tianqi, Dipta Das, Sourya, Shiue-Yuan Chuang, Bing Ouyang, Ma, Lizhuang, Murari Mandal, Liao, Tzu-Yi, Xie, Yuan, Metwaly, Kareem, Qu, Yanyun, Vincent Whannou de Dravo, Peng-Wen Chen, Xiangzhen Kong   +103 more
core   +1 more source

Weighted Dark Channel Dehazing

CoRR, 2019
In dark channel based methods, local constant assumption is widely used to make the algorithms invertible. It inevitably introduces defects since the assumption can not perfectly avoid depth discontinuities and meanwhile cover enough pixels. Unfortunately, because of the limitation of the prior, which only confirms the existence of dark things but does
Mingzhu Zhu, Bing-Wei He, Jiantao Liu
openaire   +3 more sources

Prompt-based test-time real image dehazing: a novel pipeline [PDF]

Existing methods attempt to improve models\u27 generalization ability on real-world hazy images by exploring well-designed training schemes (\eg, CycleGAN, prior loss).
Lu, Ziqian, Lu, Zhe-Ming, He, Zewei, Sun, Xuecheng, Chen, Zixuan   +4 more
core  

AgriGAN: unpaired image dehazing via a cycle-consistent generative adversarial network for the agricultural plant phenotype

Scientific Reports
Artificially extracted agricultural phenotype information exhibits high subjectivity and low accuracy, while the utilization of image extraction information is susceptible to interference from haze.
Jin-Ting Ding, Yong-Yu Peng, Min Huang, Sheng-Jun Zhou   +3 more
doaj   +1 more source

Enhance Dehazed Images Rapidly Without Losing Restoration Accuracy

IEEE Access
We proposed a novel image-enhancing framework to ensure consolidated restoration accuracy when remedying the visual quality of dehazed images, such as over-saturation, color deviation, or luminance issues. Conventionally, the dehazing process was usually
Ping-Juei Liu
doaj   +1 more source

PEIE: Physics Embedded Illumination Estimation for Adaptive Dehazing

Deep learning-based methods have made significant progress in image dehazing. However, these methods often falter when applied to real-world hazy images, primarily due to the scarcity of paired real-world data and the limitations of current dehazing ...
Liu, Huaizhuo, Jiang, Yonglong, Liu, Yurui, Hu, Hai-Miao   +3 more
core   +1 more source