HazeRD: an outdoor dataset for dehazing algorithms

Citation Author(s):
Yanfu Zhang, Li Ding, Gaurav Sharma
Submitted by:
Yanfu Zhang
Last updated:
Thu, 11/08/2018 - 10:34
DOI:
10.21227/H2001Q
Data Format:
License:
2500 Views
Categories:
Keywords:
5
1 rating - Please login to submit your rating.

Abstract 

HazeRD is an outdoor scene dataset for benchmarking dehazing algorithms. HazeRD contains 10 different scenes based on the architectural biometrics project. For each scene, the ground RGB images, depth maps, and synthesized hazy images following the atmospheric optics are provided; the hazy images come with five different haze level using real life physical parameters. The main features of HazeRD to other dehazing datasets are: HazeRD focuses on outdoor scenes whereas other datasets provide indoor scenes; and, the synthesis is based on real life parameters. 

Instructions: 

The image files are organized as each scene with synthesized images under five different weather conditions. We also provide the matlab scripts for the generation of hazy images.

The files are named as follow:

 

hazy_img_generation.m

scene_{1~10}/

    gt.png

    depth.png

    haze_{50,100,200,500,1000}.png

Comments

Good

Submitted by FAN ZIR on Fri, 11/13/2020 - 21:39

GOOD

Submitted by hunt kao on Wed, 04/28/2021 - 01:24

Can you download it? Clicking the link didn't respond

Submitted by Liu Bo on Thu, 12/24/2020 - 03:31

good

Submitted by fan zhou on Mon, 09/27/2021 - 04:10

how to download?

Submitted by pang yong on Thu, 05/26/2022 - 03:13

Files have not been uploaded for this dataset

Submitted by yiming su on Sun, 11/06/2022 - 21:23

Could not find the files.

Submitted by Cehao Yu on Thu, 09/26/2024 - 23:00

Dataset Files

    Files have not been uploaded for this dataset