ML Anthology

Consistent Segmentation for Optical Flow Estimation

C. Lawrence Zitnick, Nebojsa Jojic, Sing Bing Kang
ICCV 2005 pp. 1308-1315
doi:10.1109/ICCV.2005.61 /iccv/2005/zitnick2005iccv-consistent/

Abstract

In this paper, we propose a method for jointly computing optical flow and segmenting video while accounting for mixed pixels (matting). Our method is based on statistical modeling of an image pair using constraints on appearance and motion. Segments are viewed as overlapping regions with fractional (/spl alpha/) contributions. Bidirectional motion is estimated based on spatial coherence and similarity of segment colors. Our model is extended to video by chaining the pairwise models to produce a joint probability distribution to be maximized. To make the problem more tractable, we factorize the posterior distribution and iteratively minimize its parts. We demonstrate our method on frame interpolation.

ICCV Semantic Scholar

Cite

Text

Zitnick et al. "Consistent Segmentation for Optical Flow Estimation." IEEE/CVF International Conference on Computer Vision, 2005. doi:10.1109/ICCV.2005.61

Markdown

[Zitnick et al. "Consistent Segmentation for Optical Flow Estimation." IEEE/CVF International Conference on Computer Vision, 2005.](https://mlanthology.org/iccv/2005/zitnick2005iccv-consistent/) doi:10.1109/ICCV.2005.61

BibTeX

@inproceedings{zitnick2005iccv-consistent,
  title     = {{Consistent Segmentation for Optical Flow Estimation}},
  author    = {Zitnick, C. Lawrence and Jojic, Nebojsa and Kang, Sing Bing},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2005},
  pages     = {1308-1315},
  doi       = {10.1109/ICCV.2005.61},
  url       = {https://mlanthology.org/iccv/2005/zitnick2005iccv-consistent/}
}