Database of Fog
目录1. Ancuti系列数据集D-hazy数据集O-hazy数据集I-hazy数据集2.NYU2 Depth3. RESIDE4. RESIDE-beta(增加室外)5.去雾比赛6. NTIRE 20187.NTIRE 2019 image restoration and enhancement challenges - ONGOING!8. WI...
目录
7. NTIRE 2019 image restoration and enhancement challenges - ONGOING!
8. WILD:Weather and Illumunation Database
1. Ancuti系列数据集
-
D-hazy数据集
] C. Ancuti, C. O. Ancuti, and C. De Vleeschouwer. D-HAZY: a dataset to evaluate quantitatively dehazing algorithms. In IEEE International Conference on Image Processing (ICIP), pages 2226–2230. IEEE, 2016.
绍了如何用深度图生成雾天,使用了以下室内数据集
middlebury:http://vision.middlebury.edu/stereo/data/scenes2014/
-
O-hazy数据集
7] C. O. Ancuti, C. Ancuti, R. Timofte, and C. De Vleeschouwer. O-HAZE: a dehazing benchmark with real hazy and haze-free outdoor images. In arXiv, 2018.
-
I-hazy数据集
C. O. Ancuti, C. Ancuti, R. Timofte, and C. De Vleeschouwer. I-HAZE: a dehazing benchmark with real hazy and haze-free indoor images. In arXiv, 2018.
2.NYU2 Depth
https://cs.nyu.edu/~silberman/datasets/nyu_depth_v2.html
百度云链接及提取说明:
https://blog.csdn.net/sinat_26871259/article/details/82351276
介绍 https://www.jianshu.com/p/870c541337b4
数据及说明:https://www.jianshu.com/p/870c541337b4
3. RESIDE
https://sites.google.com/view/reside-dehaze-datasets
1)训练集 ITS(indoor training set)
室内,合成
利用1399张middlebury 和NYU2 Depth室内深度数据集 生成13990个图。一个 真实值对应10个雾天图
分成13000训练集和990验证集
2).测试集1 SOTS(synthetic objective testing set)
室内图 算法客观评价
从NYU2中选了500张(与训练集无重复),生成方式与训练集同。
3)测试集2 HSTS(Hybrid Subjecive testing set)
室外图 人主观评价
10张合成图,与test1同。10张真实图。
4. RESIDE-beta(增加室外)
OTS(outdoor training set)
用2061张来自北京实时天气的真实室外图,使用【38】“Learning depth from single monocular images using deep convolutional neural fields,”中的算法减少深度的误差和可能生成的视觉造假现象。
beta属于【0.04,0.06,0.08,0.1,0.12,0.16,0.2】7类
A属于【0.8,0.85,0.9,0.95,1】5类
所以共生成572061=72135张
real world task-driven testing set
5. 去雾比赛
这里面有广汽研究院提供真实雾霾测试数据(CHINAMM比赛数据)
https://sites.google.com/view/reside-dehaze-datasets
https://pan.baidu.com/s/1nuJOdjr 密码: n3v8
6. NTIRE 2018
https://competitions.codalab.org/competitions/18047
7. NTIRE 2019 image restoration and enhancement challenges - ONGOING!
-
Image Dehazing Challenge based on a novel dataset with pairs of real dense hazy and corresponding ground truth haze-free images, data available to the registered participants
- Image denoising challenge based on a novel dataset with pairs of real noisy and corresponding noise-free images
8. WILD:Weather and Illumunation Database
http://www.cs.columbia.edu/CAVE/software/wild/index.php
9. Fattal数据集
http://www.cs.huji.ac.il/~raananf/projects/dehaze_cl/
10. Foggy Datasets
http:// www.vision.ee.ethz.ch/~csakarid/SFSU_synthetic.
- Foggy Cityscapes
- Foggy Driving.
11. 各种合成数据集
- Middlebury Stereo Datasets合成数据集
- NYU Depth database合成数据集(有深度图)
- IMAGENET ILSVRC2012 dataset.合成
- . Pascal-voc2007合成
- web元自然图像
更多推荐
所有评论(0)