< Back to Yunfei's home page

PBRR:  Physically Based Raindrop Rendering

Yunfei Liu¹, Zhixiang Hao¹, Shadi You², Yu Li³, Feng Lu¹

1. Beihang University

2. University of Amsterdam

3. Tencent

PBRR is a large scale, public dataset for raindrop removal of photo-realistic adherent raindrop images based on Cityscapes dataset. It contains two sub-dataset. In particular, the PBRR-Spheric dataset contains14875 data-samples using spherical crown mode; and the PBRR-Bézier dataset includes 14875 data-samples using Orthogonal Bezier Curve model. Each data sample contains images with 50-70 raindrops with various but realistic appearances, a ground truth raindrop mask, and a ground truth raindrop-less image.

References

1. Porav, H., Bruls, T., Newman, P.: I can see clearly now: Image restoration via de-raining. arXiv preprint arXiv:1901.00893(2019)
2. Qian, R., Tan, R.T., Yang, W., Su, J., Liu, J.: Attentive generative adversarial network for raindrop removal from a single image. In: IEEE Conference on Computer Vision and Pattern Recognition(2018)

Citation

x
1
@Misc{Liu2019PBRR,
2
    howpublished = {[EB/OL]},
3
    note = {\url{http://liuyunfei.net/Projs/PBRR/},
4
    title = {PBRR: Physically Based Raindrop Rendering},
5
    author = {Yunfei Liu, Zhixiang Hao, Shadi You, Yu Li, and Feng Lu}
6
}

Download

The dataset can be accessed from here.