Multi-View Spectral Polarization Propagation for Video Glass Segmentation

Abstract

In this paper, we present the first polarization-guided video glass segmentation propagation solution (PGVS-Net) that can robustly and coherently propagate glass segmentation in RGB-P video sequences. By leveraging spatiotemporal polarization and color information, our method combines multi-view polarization cues and thus can alleviate the view dependence of single-input intensity variations on glass objects. We demonstrate that our model can outperform glass segmentation on RGB-only video sequences as well as produce more robust segmentation than per-frame RGB-P single-image segmentation methods. To train and validate PGVS-Net, we introduce a novel RGB-P Glass Video dataset (PGV-117) containing 117 video sequences of scenes captured with different types of camera paths, lighting conditions, dynamics, and glass types.

Cite

Text

Qiao et al. "Multi-View Spectral Polarization Propagation for Video Glass Segmentation." International Conference on Computer Vision, 2023. doi:10.1109/ICCV51070.2023.02122

Markdown

[Qiao et al. "Multi-View Spectral Polarization Propagation for Video Glass Segmentation." International Conference on Computer Vision, 2023.](https://mlanthology.org/iccv/2023/qiao2023iccv-multiview/) doi:10.1109/ICCV51070.2023.02122

BibTeX

@inproceedings{qiao2023iccv-multiview,
  title     = {{Multi-View Spectral Polarization Propagation for Video Glass Segmentation}},
  author    = {Qiao, Yu and Dong, Bo and Jin, Ao and Fu, Yu and Baek, Seung-Hwan and Heide, Felix and Peers, Pieter and Wei, Xiaopeng and Yang, Xin},
  booktitle = {International Conference on Computer Vision},
  year      = {2023},
  pages     = {23218-23228},
  doi       = {10.1109/ICCV51070.2023.02122},
  url       = {https://mlanthology.org/iccv/2023/qiao2023iccv-multiview/}
}