Shadow Removal with Paired and Unpaired Learning
Abstract
Shadow removal is an important computer vision task aiming at the detection and successful removal of the shadow produced by an occluded light source and a photorealistic restoration of the image contents. Decades of research produced a multitude of hand-crafted restoration techniques and, more recently, learned solutions from shadowed and shadow-free training image pairs. In this work, we propose a single image shadow removal solution via self-supervised learning by using a conditioned mask. We rely on self-supervision and jointly learn deep models to remove and add shadows to images. We derive two variants for learning from paired images and unpaired images, respectively. Our validation on the recently introduced ISTD and USR datasets demonstrate large quantitative and qualitative improvements over the state-of-the-art for both paired and unpaired learning settings.
Cite
Text
Vasluianu et al. "Shadow Removal with Paired and Unpaired Learning." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021. doi:10.1109/CVPRW53098.2021.00092Markdown
[Vasluianu et al. "Shadow Removal with Paired and Unpaired Learning." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021.](https://mlanthology.org/cvprw/2021/vasluianu2021cvprw-shadow/) doi:10.1109/CVPRW53098.2021.00092BibTeX
@inproceedings{vasluianu2021cvprw-shadow,
title = {{Shadow Removal with Paired and Unpaired Learning}},
author = {Vasluianu, Florin-Alexandru and Romero, Andrés and Van Gool, Luc and Timofte, Radu},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2021},
pages = {826-835},
doi = {10.1109/CVPRW53098.2021.00092},
url = {https://mlanthology.org/cvprw/2021/vasluianu2021cvprw-shadow/}
}