graviti
产品服务
解决方案
知识库
公开数据集
关于我们
Real Rain Dataset
许可协议: CC-BY-NC-SA

Overview

We propose a semi-automatic method that incorporates temporal priors and human supervision to generate a high-quality clean image from each input sequence of real rain images. Using this method, we construct a large-scale dataset of ∼29.5K rain/rain-free image pairs that cover a wide range of natural rain scenes.

数据概要
数据格式
image,
数据量
30K
文件大小
--
发布方
Rynson W.H. Lau
| 数据量 30K | 大小 --
Real Rain Dataset
许可协议: CC-BY-NC-SA

Overview

We propose a semi-automatic method that incorporates temporal priors and human supervision to generate a high-quality clean image from each input sequence of real rain images. Using this method, we construct a large-scale dataset of ∼29.5K rain/rain-free image pairs that cover a wide range of natural rain scenes.

0
立即开始构建AI
graviti
wechat-QR
长按保存识别二维码,关注Graviti公众号

Copyright@Graviti
沪ICP备19019574号
沪公网安备 31011002004865号