ML Anthology

Binocular Helmholtz Stereopsis

Todd E. Zickler, Jeffrey Ho, David J. Kriegman, Jean Ponce, Peter N. Belhumeur
ICCV 2003 pp. 1411-1417
doi:10.1109/ICCV.2003.1238655 /iccv/2003/zickler2003iccv-binocular/

Abstract

Helmholtz stereopsis has been introduced recently as a surface reconstruction technique that does not assume a model of surface reflectance. In the reported formulation, correspondence was established using a rank constraint, necessitating at least three viewpoints and three pairs of images. Here, it is revealed that the fundamental Helmholtz stereopsis constraint defines a nonlinear partial differential equation, which can be solved using only two images. It is shown that, unlike conventional stereo, binocular Helmholtz stereopsis is able to establish correspondence (and thereby recover surface depth) for objects having an arbitrary and unknown BRDF and in textureless regions (i.e., regions of constant or slowly varying BRDF). An implementation and experimental results validate the method for specular surfaces with and without texture. 1

PDF ICCV Semantic Scholar

Cite

Text

Zickler et al. "Binocular Helmholtz Stereopsis." IEEE/CVF International Conference on Computer Vision, 2003. doi:10.1109/ICCV.2003.1238655

Markdown

[Zickler et al. "Binocular Helmholtz Stereopsis." IEEE/CVF International Conference on Computer Vision, 2003.](https://mlanthology.org/iccv/2003/zickler2003iccv-binocular/) doi:10.1109/ICCV.2003.1238655

BibTeX

@inproceedings{zickler2003iccv-binocular,
  title     = {{Binocular Helmholtz Stereopsis}},
  author    = {Zickler, Todd E. and Ho, Jeffrey and Kriegman, David J. and Ponce, Jean and Belhumeur, Peter N.},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2003},
  pages     = {1411-1417},
  doi       = {10.1109/ICCV.2003.1238655},
  url       = {https://mlanthology.org/iccv/2003/zickler2003iccv-binocular/}
}