S3R-Net: A Single-Stage Approach to Self-Supervised Shadow Removal
Abstract
In this paper we present S3R-Net, the Self-Supervised Shadow Removal Network. The two-branch WGAN model achieves self-supervision1 relying on the unify-and-adapt phenomenon - it unifies the style of the output data and infers its characteristics from a database of unaligned shadow-free reference images. This approach stands in contrast to the large body of supervised frameworks. S3R-Net also differentiates itself from the few existing self-supervised models operating in a cycle-consistent manner, as it is a non-cyclic, unidirectional solution. The proposed framework achieves comparable numerical scores to recent self-supervised shadow removal models while exhibiting superior qualitative performance and keeping the computational cost low. The pre-trained models and the code can be found in our github repo.
Cite
Text
Kubiak et al. "S3R-Net: A Single-Stage Approach to Self-Supervised Shadow Removal." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2024. doi:10.1109/CVPRW63382.2024.00597Markdown
[Kubiak et al. "S3R-Net: A Single-Stage Approach to Self-Supervised Shadow Removal." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2024.](https://mlanthology.org/cvprw/2024/kubiak2024cvprw-s3rnet/) doi:10.1109/CVPRW63382.2024.00597BibTeX
@inproceedings{kubiak2024cvprw-s3rnet,
title = {{S3R-Net: A Single-Stage Approach to Self-Supervised Shadow Removal}},
author = {Kubiak, Nikolina and Mustafa, Armin and Phillipson, Graeme and Jolly, Stephen and Hadfield, Simon},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2024},
pages = {5898-5908},
doi = {10.1109/CVPRW63382.2024.00597},
url = {https://mlanthology.org/cvprw/2024/kubiak2024cvprw-s3rnet/}
}