README.md~

<img src='Test/lssd1005.jpg' width=200 height = 250> <img src='out/lssd1005.jpg'  width=200 height =250> 
<br><br><br>



# A+D-Net: Shadow Detection with Adversarial Shadow Attenuation


This is a demo of [ADNet for shadow detection](https://arxiv.org/abs/1712.01361). The code is written by [Hieu Le](https://lmhieu612.github.io). A large amount of code is borrowed from the pix2pix implementation of Jan-Yan-Zhu and Teasung Park. 

Download the model at:

https://drive.google.com/file/d/1SObzFGNFGRZ8pvYJGTwQh3Nwyi7wX7G-/view?usp=sharing

## Citation
If you use this code for your research, please cite:

```
A+D-Net: Shadow Detection with Adversarial Shadow Attenuation
Hieu Le, Tomas F. Yago Vicente, Vu Nguyen, Minh Hoai, Dimitris Samaras

@inproceedings{m_Le-etal-ECCV18, 
Author = {Hieu Le and Tomas F. Yago Vicente and Vu Nguyen and Minh Hoai and Dimitris Samaras}, 
Booktitle = {Proceedings of European Conference on Computer Vision}, 
Title = {{A+D Net}: Training a Shadow Detector with Adversarial Shadow Attenuation}, 
Year = {2018}} 
```