HazeSpace2M is a large scale paired hazy dataset for training and evaluating haze type classification models and single image dehazing models.

Exclusive selection of luxury cars for rent

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

🌫️ Haze Removal with Dark Prior Channel 🌫️ "We’re tackling hazy images using the Dark Prior Channel method, which clears haze, dust, and fog by analyzing pixel intensity. 🚀 While we’ve seen promising results, limited resources impact our full dehazing capability. 🖼️✨ Our work enhances image clarity and contributes to haze removal techniques."

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.

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

A simple app that demonstrates implementing BottomNavigation in Glassmorphic style

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.

Facial recognition chat app made with openCV for iphone and ipad

Weather App with JavaScript and API

Dark Channel Prior Dehazing implementation for IOS using Swift 5

An Improved Air-Light Estimation Scheme for Single Haze Images Using Color Constancy Prior.

easy retrieval of pollutant/air quality information/haze levels from NEA APIs at data.gov.sg

Comparing two countries definition of healthy air

Three fog/haze-removal papers implementation.

An c++ implementation of 《single image haze removal using dark channel prior》

Haze Removal tool using Dark Channel Prior. Based on work by Kaiming He.

A quickly hacked up PSI OS X status bar app