Exploiting high level scene cues in stereo reconstruction (bibtex)

by Simon Hadfield and Richard Bowden

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.

View PDF

Reference:

Exploiting high level scene cues in stereo reconstruction (Simon Hadfield and Richard Bowden), In Proceedings of the International Conference on Computer Vision (ICCV), IEEE, 2015. (Spotlight video, Supplementary Results, Poster)

Bibtex Entry:

@InProceedings{Hadfield15,
  Title                    = {Exploiting high level scene cues in stereo reconstruction},
  Author                   = {Simon Hadfield and Richard Bowden},
  Booktitle                = {Proceedings of the International Conference on Computer Vision (ICCV)},
  Year                     = {2015},

  Address                  = {Santiago, Chile},
  Month                    = {10 -- 18 } # dec,
  Organization             = {IEEE},
  Publisher                = {IEEE},
  Pages = {783 -- 791},
  Doi = {10.1109/ICCV.2015.96},
  Gsid = {924967012361300357},
  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.},
  Comment                  = {<a href="https://youtu.be/tgvHHkxis4A">Spotlight video</a>, <a href="http://personalpages.surrey.ac.uk/s.hadfield/papers/Exploiting%20high%20level%20scene%20cues%20in%20stereo%20reconstruction-supp.pdf">Supplementary Results</a>, <a href="http://personalpages.surrey.ac.uk/s.hadfield/posters/Exploiting%20high%20level%20scene%20cues%20in%20stereo%20reconstruction.pdf">Poster</a>},
  Crossref                 = {ICCV15},
  Url                      = {http://personalpages.surrey.ac.uk/s.hadfield/papers/Exploiting%20high%20level%20scene%20cues%20in%20stereo%20reconstruction.pdf}
}