Exploiting High Level Scene Cues in Stereo Reconstruction

ICCV 2015

doi:10.1109/ICCV.2015.96 /iccv/2015/hadfield2015iccv-exploiting/

Abstract

We present a novel approach to 3D reconstruction which is inspired by the human visual system. This system unifies standard appearance matching and triangulation techniques with higher level reasoning and scene understanding, in order to resolve ambiguities between different interpretations of the scene. The types of reasoning integrated in the approach includes recognising common configurations of surface normals and semantic edges (e.g. convex, concave and occlusion boundaries). We also recognise the coplanar, collinear and symmetric structures which are especially common in man made environments.

PDF ICCV Semantic Scholar

Cite

Text

Hadfield and Bowden. "Exploiting High Level Scene Cues in Stereo Reconstruction." International Conference on Computer Vision, 2015. doi:10.1109/ICCV.2015.96

Markdown

[Hadfield and Bowden. "Exploiting High Level Scene Cues in Stereo Reconstruction." International Conference on Computer Vision, 2015.](https://mlanthology.org/iccv/2015/hadfield2015iccv-exploiting/) doi:10.1109/ICCV.2015.96

BibTeX

@inproceedings{hadfield2015iccv-exploiting,
  title     = {{Exploiting High Level Scene Cues in Stereo Reconstruction}},
  author    = {Hadfield, Simon and Bowden, Richard},
  booktitle = {International Conference on Computer Vision},
  year      = {2015},
  doi       = {10.1109/ICCV.2015.96},
  url       = {https://mlanthology.org/iccv/2015/hadfield2015iccv-exploiting/}
}