On 3D Scene Flow and Structure Estimation

CVPR 2001 pp. II:778-785

doi:10.1109/CVPR.2001.991044 /cvpr/2001/zhang2001cvpr-d/

Abstract

In this paper, novel algorithms computing dense 3D scene flow from multiview image sequences are described. A new hierarchical rule-based stereo matching algorithm is presented to estimate the initial disparity map. Different available constraints under a multiview camera setup are investigated and then utilized in the proposed motion estimation algorithms. We show two different formulations for 3D scene flow computation. One formulation assumes that initial disparity map is accurate while the other does not make this assumption. Image segmentation information is used to maintain the motion and depth discontinuities. Iterative implementations are used to successfully compute 3D scene flow and structure at every point in the reference image. Novel hard constraints are introduced in this paper to make the algorithms more accurate and robust. Promising experimental results are seen by applying our algorithms to real imagery.

CVPR Semantic Scholar

Cite

Text

Zhang and Kambhamettu. "On 3D Scene Flow and Structure Estimation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001. doi:10.1109/CVPR.2001.991044

Markdown

[Zhang and Kambhamettu. "On 3D Scene Flow and Structure Estimation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001.](https://mlanthology.org/cvpr/2001/zhang2001cvpr-d/) doi:10.1109/CVPR.2001.991044

BibTeX

@inproceedings{zhang2001cvpr-d,
  title     = {{On 3D Scene Flow and Structure Estimation}},
  author    = {Zhang, Ye and Kambhamettu, Chandra},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2001},
  pages     = {II:778-785},
  doi       = {10.1109/CVPR.2001.991044},
  url       = {https://mlanthology.org/cvpr/2001/zhang2001cvpr-d/}
}