The dataset consists of two parts: rainy dataset and hazy dataset. Both these two datasets including training,
validation, and test data.
Hazy dataset: We provide 3,000 real-world hazy images collected from traffic surveillance scene,
all of which are labeled with object bounding boxes and categories (car, bus, bicycle, motorcycle,
and pedestrian), for validation and testing purposes.
[Baidu Yun] Passward: w54h
Rainy dataset: We provide 2,495 real rainy images from high-resolution driving videos.
They were captured in diverse real traffic locations and scenes during multiple drives, all of which
are labeled with object bounding boxes and categories: car, person, bus, bicycle, and motorcycle.
1. Additional training data is allowed in this challenge.
2. Please KEEP the NAMES and the original RESOLUTION of testing images when submitting your
results. You can share the derained/dehazed results and the code to us via Baidu Yun, Google Drive,
or Dropbox. Only the last submission will be valid. Please send the shared link to firstname.lastname@example.org
with your team name. You may visit the
to submit your accompanying paper. Both DEADLINEs of submission of testing images and the accompanying paper
(paper submission is optional) are May 27.