Several image/video enhancement methods, implemented by Java, to tackle common tasks, like dehazing, denoising, backscatter removal, low illuminance enhancement, featuring, smoothing and etc.

[ACMMM2023] "Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution", https://arxiv.org/abs/2308.01738

[CVPR 2022] Learning Multiple Adverse Weather Removal via Two-stage Knowledge Learning and Multi-contrastive Regularization: Toward a Unified Model

python implementation of the paper: "Efficient Image Dehazing with Boundary Constraint and Contextual Regularization"

This paper is accepted by ICCV 2021.

Depth-Attentional Features for Single-Image Rain Removal and RainCityscapes Dataset | CVPR 2019

[CVPR 2009] Single Image Haze Removal Using Dark Channel Prior

A Python2 implementation of single image haze removal

Image Brightness Enhancement Automatically Based on Fast Haze Removal

EDN-GTM for Single Image Dehazing

This is the source code of PMHLD-Patch-Map-Based-Hybrid-Learning-DehazeNet-for-Single-Image-Haze-Removal which has been accepted by IEEE Transaction on Image Processing 2020.

DGNL-Net and RainCityscapes

This is the project page of our paper which has been published in ECCV 2020.

The Dark Channel Prior technique is implemented on FPGA using only Verilog code and no Intellectual Property, making it convenient to replicate using any simulator and any of the available FPGA boards, including those from Xilinx and Altera.

Conditional Wasserstein Generative Adversarial Network for image-to-image translation.

A cross-platform image dehazing/defogging mobile app implemented with React Native, Djinni and OpenCV, based on dark channel prior and fast guided filter.

This is the source code of PMS-Net: Robust Haze Removal Based on Patch Map for Single Images which has been published in CVPR 2019 Long Beach

A Matlab implementation of haze removal from a single image (RGB and Grayscale)

Code of the paper "Learning a Patch Quality Comparator for Single Image Dehazing"

The code for haze removal using dark channel prior, which was a part of the self-driving car project