LTNet: Light Transfer Network for Depth Guided Image Relighting
Abstract
Relighting is an interesting yet challenging low-level vision problem, which aims to re-render the scene with new light sources. In this paper, we introduce LTNet, a novel framework for image relighting. Unlike previous methods, we propose to solve this challenging problem by decoupling the enhancement process. Specifically, we propose to train a network that focuses on learning light variations. Our key insight is that light variations are the critical information to be learned because the scene stays unchanged during the light transfer process. To this end, we employ a global residual connection and corresponding residual loss for capturing light variations. Experimental results show that the proposed method achieves better visual quality on the VIDIT dataset in the NTIRE2021 relighting challenge.
Cite
Text
Zhu et al. "LTNet: Light Transfer Network for Depth Guided Image Relighting." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021. doi:10.1109/CVPRW53098.2021.00033Markdown
[Zhu et al. "LTNet: Light Transfer Network for Depth Guided Image Relighting." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021.](https://mlanthology.org/cvprw/2021/zhu2021cvprw-ltnet/) doi:10.1109/CVPRW53098.2021.00033BibTeX
@inproceedings{zhu2021cvprw-ltnet,
title = {{LTNet: Light Transfer Network for Depth Guided Image Relighting}},
author = {Zhu, Yu and Ding, Bosong and Li, Chenghua and Qian, Wanli and Li, Fangya and Yao, Yiheng and Gang, Ruipeng and Zhang, Chunjie and Cheng, Jian},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2021},
pages = {243-251},
doi = {10.1109/CVPRW53098.2021.00033},
url = {https://mlanthology.org/cvprw/2021/zhu2021cvprw-ltnet/}
}