ML Anthology

View-Consistent 4D Light Field Superpixel Segmentation

Numair Khan, Qian Zhang, Lucas Kasser, Henry Stone, Min H. Kim, James Tompkin
ICCV 2019
doi:10.1109/ICCV.2019.00790 /iccv/2019/khan2019iccv-viewconsistent/

Abstract

Many 4D light field processing applications rely on superpixel segmentations, for which occlusion-aware view consistency is important. Yet, existing methods often enforce consistency by propagating clusters from a central view only, which can lead to inconsistent superpixels for non-central views. Our proposed approach combines an occlusion-aware angular segmentation in horizontal and vertical EPI spaces with an occlusion-aware clustering and propagation step across all views. Qualitative video demonstrations show that this helps to remove flickering and inconsistent boundary shapes versus the state-of-the-art approach, and quantitative metrics reflect these findings with improved boundary accuracy and view consistency scores.

PDF ICCV Semantic Scholar

Cite

Text

Khan et al. "View-Consistent 4D Light Field Superpixel Segmentation." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019. doi:10.1109/ICCV.2019.00790

Markdown

[Khan et al. "View-Consistent 4D Light Field Superpixel Segmentation." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019.](https://mlanthology.org/iccv/2019/khan2019iccv-viewconsistent/) doi:10.1109/ICCV.2019.00790

BibTeX

@inproceedings{khan2019iccv-viewconsistent,
  title     = {{View-Consistent 4D Light Field Superpixel Segmentation}},
  author    = {Khan, Numair and Zhang, Qian and Kasser, Lucas and Stone, Henry and Kim, Min H. and Tompkin, James},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  year      = {2019},
  doi       = {10.1109/ICCV.2019.00790},
  url       = {https://mlanthology.org/iccv/2019/khan2019iccv-viewconsistent/}
}