Dehazing is a process of removal of haze from the photography of a hazy scene. The method adopted here is using Contextual Regularization.
-
Updated
Feb 2, 2022 - Python
Dehazing is a process of removal of haze from the photography of a hazy scene. The method adopted here is using Contextual Regularization.
Dehazing enhances surveillance and remote sensing by improving image clarity for better detection and analysis.
Implementation of All-In-One-Dehazing Network in Tensorflow V2.
NTIRE-2021-Dehazing-Two-branchをGoogle Colaboratory上で推論実行するサンプル
In this Project, important algorithms such as Canny Edge Detection, Harris Corner Detection, Segmentation, and Dehazing are utilized. These algorithms perform operations like detecting edges and corners in images, segmenting different regions, and enhancing foggy or blurred images.
Enhancing satellite image clarity by removing haze using AOD-Net's deep convolutional and residual architectures
Enhancing satellite image clarity by removing haze using AOD-Net's deep convolutional and residual architectures
Single image dehazing via an improved atmospheric scattering model
The official code of the IEEE Access paper Multiple Adverse Weather Removal Using Masked-Based Pre-Training and Dual-Pooling Adaptive Convolution (MPDAC)
Source code for book "Image algorithms for low-level vision tasks" (Jia. 2024), including denoising, super-resolution, dehazing, image composition and enhancement models and algorithms implemented in pure Python.
Official repository for the paper "Image Dehazing via Joint Estimation of Transmittance Map and Environmental Illumination"
This is a MATLAB source code of the enhanced equidistribution, which guarantees that the generated random sequence follows the theoretical uniform distribution.
An Improved Air-Light Estimation Scheme for Single Haze Images Using Color Constancy Prior.
Region-Based Dehazing via Dual-Supervised Triple-Convolutional Network
This preoject is for our paper SINGLE IMAGE HAZE REMOVAL VIA JOINT ESTIMATION OF DETAIL AND TRANSMISSION
Gated Fusion Network for Degraded Image Super-Resolution (IJCV 2020).
This is the official PyTorch implementation of DehazeDCT. Our method achieves the second best performance in NTIRE 2024 Dense and NonHomogeneous Dehazing Challenge (CVPR workshop))
This is an improved version of the deblurring of faces. It shows about 5% increase in SSIM metric in comparison with the original methods. Tweaked the existing dehazing algorithms to work for deblurring.
Improve performance of PWC-Net in foggy scenes
Add a description, image, and links to the dehazing topic page so that developers can more easily learn about it.
To associate your repository with the dehazing topic, visit your repo's landing page and select "manage topics."