ML Anthology

Reflection Scene Separation from a Single Image

Renjie Wan, Boxin Shi, Haoliang Li, Ling-Yu Duan, Alex C. Kot
CVPR 2020
doi:10.1109/CVPR42600.2020.00247 /cvpr/2020/wan2020cvpr-reflection/

Abstract

For images taken through glass, existing methods focus on the restoration of the background scene by regarding the reflection components as noise. However, the scene reflected by glass surface also contains important information to be recovered, especially for the surveillance or criminal investigations. In this paper, instead of removing reflection components from the mixture image, we aim at recovering reflection scenes from the mixture image. We first propose a strategy to obtain such ground truth and its corresponding input images. Then, we propose a two-stage framework to obtain the visible reflection scene from the mixture image. Specifically, we train the network with a shift-invariant loss which is robust to misalignment between the input and output images. The experimental results show that our proposed method achieves promising results.

PDF CVPR Semantic Scholar

Cite

Text

Wan et al. "Reflection Scene Separation from a Single Image." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020. doi:10.1109/CVPR42600.2020.00247

Markdown

[Wan et al. "Reflection Scene Separation from a Single Image." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.](https://mlanthology.org/cvpr/2020/wan2020cvpr-reflection/) doi:10.1109/CVPR42600.2020.00247

BibTeX

@inproceedings{wan2020cvpr-reflection,
  title     = {{Reflection Scene Separation from a Single Image}},
  author    = {Wan, Renjie and Shi, Boxin and Li, Haoliang and Duan, Ling-Yu and Kot, Alex C.},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2020},
  doi       = {10.1109/CVPR42600.2020.00247},
  url       = {https://mlanthology.org/cvpr/2020/wan2020cvpr-reflection/}
}