Results 101 to 110 of about 303 (154)
Cycle-Dehaze: Enhanced CycleGAN for Single Image Dehazing [PDF]
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018 Accepted at CVPRW: NTIRE ...
Hazım Kemal Ekenel
exaly +6 more sources
UR2P-Dehaze: Learning a Simple Image Dehaze Enhancer via Unpaired Rich Physical Prior
Pattern RecognitionImage dehazing techniques aim to enhance contrast and restore details, which are essential for preserving visual information and improving image processing accuracy.
Shivakumara Palaiahnakote +2 more
exaly +7 more sources
Some of the next articles are maybe not open access.
Related searches:
Related searches:
Knowledge Transfer Dehazing Network for NonHomogeneous Dehazing
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2020Single image dehazing is an ill-posed problem that has recently drawn important attention. It is a challenging image process task, especially in nonhomogeneous scene. However, the existing dehazing methods are commonly designed to handle homogeneous haze which is easily violated in practice, due to the unknown haze distribution of real world.
Haiyan Wu +4 more
openaire +2 more sources
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
Dehaze-UNet: A Lightweight Network Based on UNet for Single-Image Dehazing
ElectronicsNumerous extant image dehazing methods based on learning improve performance by increasing the depth or width, the size of the convolution kernel, or using the Transformer structure.
Hao Zhou, Tao Tao
exaly +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
Dehaze-RetinexGAN: Real-World Image Dehazing via Retinex-Based Generative Adversarial Network
Proceedings of the AAAI Conference on Artificial IntelligenceDeep learning based dehazing networks trained on paired synthetic data have shown impressive performance, but they struggle with significant degradation in generalization ability on real-world hazy scenes.
Xinran Wang, Tian Ye
exaly +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