ML Anthology

Variational Stereovision and 3D Scene Flow Estimation with Statistical Similarity Measures

Jean-Philippe Pons, Renaud Keriven, Olivier D. Faugeras, Gerardo Hermosillo
ICCV 2003 pp. 597-602
doi:10.1109/ICCV.2003.1238402 /iccv/2003/pons2003iccv-variational/

Abstract

We present a common variational framework for dense depth recovery and dense three-dimensional motion field estimation from multiple video sequences, which is robust to camera spectral sensitivity differences and illumination changes. For this purpose, we first show that both problems reduce to a generic image matching problem after backprojecting the input images onto suitable surfaces. We then solve this matching problem in the case of statistical similarity criteria that can handle frequently occurring nonaffine image intensities dependencies. Our method leads to an efficient and elegant implementation based on fast recursive filters. We obtain good results on real images.

PDF ICCV Semantic Scholar

Cite

Text

Pons et al. "Variational Stereovision and 3D Scene Flow Estimation with Statistical Similarity Measures." IEEE/CVF International Conference on Computer Vision, 2003. doi:10.1109/ICCV.2003.1238402

Markdown

[Pons et al. "Variational Stereovision and 3D Scene Flow Estimation with Statistical Similarity Measures." IEEE/CVF International Conference on Computer Vision, 2003.](https://mlanthology.org/iccv/2003/pons2003iccv-variational/) doi:10.1109/ICCV.2003.1238402

BibTeX

@inproceedings{pons2003iccv-variational,
  title     = {{Variational Stereovision and 3D Scene Flow Estimation with Statistical Similarity Measures}},
  author    = {Pons, Jean-Philippe and Keriven, Renaud and Faugeras, Olivier D. and Hermosillo, Gerardo},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2003},
  pages     = {597-602},
  doi       = {10.1109/ICCV.2003.1238402},
  url       = {https://mlanthology.org/iccv/2003/pons2003iccv-variational/}
}