Single Image Shadow Removal via Neighbor-Based Region Relighting
Abstract
In this paper we present a novel method for shadow removal in single images. For each shadow region we use a trained classifier to identify a neighboring lit region of the same material. Given a pair of lit-shadow regions we perform a region relighting transformation based on histogram matching of luminance values between the shadow region and the lit region. Then, we adjust the CIELAB $a$ and $b$ channels of the shadow region by adding constant offsets based on the difference of the median shadow and lit pixel values. We demonstrate that our approach produces results that outperform the state of the art by evaluating our method using a publicly available benchmark dataset.
Cite
Text
Vicente and Samaras. "Single Image Shadow Removal via Neighbor-Based Region Relighting." European Conference on Computer Vision, 2014. doi:10.1007/978-3-319-16199-0_22Markdown
[Vicente and Samaras. "Single Image Shadow Removal via Neighbor-Based Region Relighting." European Conference on Computer Vision, 2014.](https://mlanthology.org/eccv/2014/vicente2014eccv-single/) doi:10.1007/978-3-319-16199-0_22BibTeX
@inproceedings{vicente2014eccv-single,
title = {{Single Image Shadow Removal via Neighbor-Based Region Relighting}},
author = {Vicente, Tomás F. Yago and Samaras, Dimitris},
booktitle = {European Conference on Computer Vision},
year = {2014},
pages = {309-320},
doi = {10.1007/978-3-319-16199-0_22},
url = {https://mlanthology.org/eccv/2014/vicente2014eccv-single/}
}