Language-Guided Image Reflection Separation
Abstract
This paper studies the problem of language-guided reflection separation which aims at addressing the ill-posed reflection separation problem by introducing language descriptions to provide layer content. We propose a unified framework to solve this problem which leverages the cross-attention mechanism with contrastive learning strategies to construct the correspondence between language descriptions and image layers. A gated network design and a randomized training strategy are employed to tackle the recognizable layer ambiguity. The effectiveness of the proposed method is validated by the significant performance advantage over existing reflection separation methods on both quantitative and qualitative comparisons.
Cite
Text
Zhong et al. "Language-Guided Image Reflection Separation." Conference on Computer Vision and Pattern Recognition, 2024. doi:10.1109/CVPR52733.2024.02353Markdown
[Zhong et al. "Language-Guided Image Reflection Separation." Conference on Computer Vision and Pattern Recognition, 2024.](https://mlanthology.org/cvpr/2024/zhong2024cvpr-languageguided/) doi:10.1109/CVPR52733.2024.02353BibTeX
@inproceedings{zhong2024cvpr-languageguided,
title = {{Language-Guided Image Reflection Separation}},
author = {Zhong, Haofeng and Hong, Yuchen and Weng, Shuchen and Liang, Jinxiu and Shi, Boxin},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2024},
pages = {24913-24922},
doi = {10.1109/CVPR52733.2024.02353},
url = {https://mlanthology.org/cvpr/2024/zhong2024cvpr-languageguided/}
}