Deep Learning for Seeing Through Window With Raindrops

Yuhui Quan, Shijie Deng, Yixin Chen, Hui Ji; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 2463-2471

Abstract


When taking pictures through glass window in rainy day, the images are comprised and corrupted by the raindrops adhered to glass surfaces. It is a challenging problem to remove the effect of raindrops from an image. The key task is how to accurately and robustly identify the raindrop regions in an image. This paper develops a convolutional neural network (CNN) for removing the effect of raindrops from an image. In the proposed CNN, we introduce a double attention mechanism that concurrently guides the CNN using shape-driven attention and channel re-calibration. The shape-driven attention exploits physical shape priors of raindrops, i.e. convexness and contour closedness, to accurately locate raindrops, and the channel re-calibration improves the robustness when processing raindrops with varying appearances. The experimental results show that the proposed CNN outperforms the state-of-the-art approaches in terms of both quantitative metrics and visual quality.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Quan_2019_ICCV,
author = {Quan, Yuhui and Deng, Shijie and Chen, Yixin and Ji, Hui},
title = {Deep Learning for Seeing Through Window With Raindrops},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}