RESIDE-β
A Benchmark for Single Image Dehazing
Extended Version
Embedded Files
News :
> We have fixed and updated Dropbox links. Please feel free to utilize it. 02/2021
> We have updated OTS dataset. Please feel free to utilize it. 07/2018
>Our standard version is available in RESIDE-Standard. Please feel free to utilize it.
Please check our updated manuscript for why and how we divide RESIDE into the standard and beta parts. Feel free to use them seperately or as one to evaluate your algorithm.
We're preparing a leaderboard and you're welcome to send in your results to be included in our website & manuscript.
Abstract
Abstract
We present a comprehensive study and evaluation of existing single image dehazing algorithms, using a new large-scale benchmark consisting of both synthetic and real-world hazy images, called REalistic Single Image DEhazing (RESIDE). RESIDE highlights diverse data sources and image contents, and is divided into five subsets, each serving different training or evaluation purposes. We further provide a rich variety of criteria for dehazing algorithm evaluation, ranging from full-reference metrics, to no-reference metrics, to subjective evaluation and the novel task-driven evaluation. Experiments on RESIDE sheds light on the comparisons and limitations of state-of-the-art dehazing algorithms, and suggest promising future directions.
Overview
Overview
Dataset Examples:
Dataset Examples:
Paper
Paper
Benchmarking Single Image Dehazing and Beyond [arXiv version]
Bibtex
Bibtex
@article{li2019benchmarking,
title={Benchmarking Single-Image Dehazing and Beyond},
author={Li, Boyi and Ren, Wenqi and Fu, Dengpan and Tao, Dacheng and Feng, Dan and Zeng, Wenjun and Wang, Zhangyang},
journal={IEEE Transactions on Image Processing},
volume={28},
number={1},
pages={492--505},
year={2019},
publisher={IEEE}
}
Download RESIDE-β Dataset
Download RESIDE-β Dataset
OTS (Outdoor Training Set)：
（Dropbox）： https://bit.ly/3k8a0Gf
（Baidu Yun）: https://pan.baidu.com/s/1YMYUp5P6FpX_5b7emjgrvA Passward: w54h
RTTS (Real-world Task-Driven Testing Set)：
（Dropbox） ：https://bit.ly/3c4gl3z
（Baidu Yun） ：https://pan.baidu.com/s/1A0MMAnlWmuJ0dXhsbXk4Gg Passward: 4mv7
Unannotated Real-world Hazy Images:
（Dropbox） ：https://bit.ly/2XVx7tc
（Baidu Yun） : https://pan.baidu.com/s/1i5GiZsx Password：vt99
Note: For Baidu Yun Link, you might need to refresh again or copy the link to a new webpage if it fails to redirect.
请注意：如果您无法直接点击百度云链接访问，请开启一个新的网页并复制链接到地址栏。
How to Use RTTS
How to Use RTTS
RTTS is in the same format as VOC 2007, organized as follows:
-- HazeDetection
-- Annotations
-- *** .xml
-- ImageSets
-- Main
-- test.txt
-- JPEGImages
-- *** .png
Here is a demo script to visualize the annotations: visualize.py, which shows how to get access to the annotated bounding boxes.
Contact
Contact
Boyi Li (boyilics@gmail.com)
Wenqi Ren (rwq.renwenqi@gmail.com)
Zhangyang Wang (atlaswang@tamu.edu)
Google Sites
Report abuse