Results 131 to 140 of about 1,385 (183)
Some of the next articles are maybe not open access.
2015 Colour and Visual Computing Symposium (CVCS), 2015
Today, there are typically two main approaches for dehazing, that is, enhancing images taken in hazy or foggy conditions. The first method is based on general image enhancement techniques where algorithms such as histogram equalization or Retinex are often used.
Vincent Jacob Whannou de Dravo +1 more
openaire +2 more sources
Today, there are typically two main approaches for dehazing, that is, enhancing images taken in hazy or foggy conditions. The first method is based on general image enhancement techniques where algorithms such as histogram equalization or Retinex are often used.
Vincent Jacob Whannou de Dravo +1 more
openaire +2 more sources
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2020
Most existing dehazing methods are not robust to nonhomogeneous haze. Meanwhile, the information of dense haze region is usually unknown and hard to estimate, leading to blurry in dehaze result for those regions. Focusing on these two issues, we propose a novel coarse-to-fine model, namely Trident Dehazing Network (TDN), to learn the hazy to hazy- free
Jing Liu 0031 +4 more
openaire +1 more source
Most existing dehazing methods are not robust to nonhomogeneous haze. Meanwhile, the information of dense haze region is usually unknown and hard to estimate, leading to blurry in dehaze result for those regions. Focusing on these two issues, we propose a novel coarse-to-fine model, namely Trident Dehazing Network (TDN), to learn the hazy to hazy- free
Jing Liu 0031 +4 more
openaire +1 more source
ICycleGAN: Single image dehazing based on iterative dehazing model and CycleGAN
Computer Vision and Image Understanding, 2021Abstract The current competitive approaches to restoring haze-free images are mainly based on physical models and learning methods. Maintaining detail information of the image while thoroughly removing fog is a challenging task in single-image dehazing.
Ziyi Sun +5 more
openaire +2 more sources
Uncertainty-Driven Dehazing Network
Proceedings of the AAAI Conference on Artificial Intelligence, 2022Deep learning has made remarkable achievements for single image haze removal. However, existing deep dehazing models only give deterministic results without discussing the uncertainty of them. There exist two types of uncertainty in the dehazing models: aleatoric uncertainty that comes from noise inherent in the observations and epistemic uncertainty
Ming Hong +3 more
openaire +2 more sources
Stereo Refinement Dehazing Network
IEEE Transactions on Circuits and Systems for Video Technology, 2022The 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
Jing Nie +4 more
openaire +2 more sources
Physically Plausible Dehazing for Non-physical Dehazing Algorithms
2019Images affected by haze usually present faded colours and loss of contrast, hindering the precision of methods devised for clear images. For this reason, image dehazing is a crucial pre-processing step for applications such as self-driving vehicles or tracking.
Javier Vazquez-Corral +2 more
openaire +3 more sources
The Visual Computer, 2021
Image dehazing aims to remove the haze noise and restore the image content from hazy images. It is a challenging task because of the unbalanced distribution of the haze noise and the variety of the image contents. Most existing methods apply convolutional neural networks to learn the dehazing process by blind end-to-end training, which relies on the ...
Fei Yang, Qian Zhang
openaire +1 more source
Image dehazing aims to remove the haze noise and restore the image content from hazy images. It is a challenging task because of the unbalanced distribution of the haze noise and the variety of the image contents. Most existing methods apply convolutional neural networks to learn the dehazing process by blind end-to-end training, which relies on the ...
Fei Yang, Qian Zhang
openaire +1 more source
2018
Haze is a major problem in videos captured in outdoors. Unlike single-image dehazing, video-based approaches can take advantage of the abundant information that exists across neighboring frames. In this work, assuming that a scene point yields highly correlated transmission values between adjacent video frames, we develop a deep learning solution for ...
Wenqi Ren, Xiaochun Cao
openaire +1 more source
Haze is a major problem in videos captured in outdoors. Unlike single-image dehazing, video-based approaches can take advantage of the abundant information that exists across neighboring frames. In this work, assuming that a scene point yields highly correlated transmission values between adjacent video frames, we develop a deep learning solution for ...
Wenqi Ren, Xiaochun Cao
openaire +1 more source
IEEE Transactions on Image Processing, 2020
In this paper, we study two less-touched challenging problems in single image dehazing neural networks, namely, how to remove haze from a given image in an unsupervised and zeroshot manner. To the ends, we propose a novel method based on the idea of layer disentanglement by viewing a hazy image as the entanglement of several "simpler" layers, i.e., a ...
Boyun Li +5 more
openaire +2 more sources
In this paper, we study two less-touched challenging problems in single image dehazing neural networks, namely, how to remove haze from a given image in an unsupervised and zeroshot manner. To the ends, we propose a novel method based on the idea of layer disentanglement by viewing a hazy image as the entanglement of several "simpler" layers, i.e., a ...
Boyun Li +5 more
openaire +2 more sources
Self-Parameter Distillation Dehazing
IEEE Transactions on Image Processing, 2023In this paper, we propose a novel dehazing method based on self-distillation. In contrast to conventional knowledge distillation approaches that transfer large models (teacher networks) to small models (student networks), we introduce a single knowledge distillation network that transfers network parameters to itself for dehazing.
Guisik Kim, Junseok Kwon
openaire +3 more sources