Dense Rigid Reconstruction from Unstructured Discontinuous Video (bibtex)
by Karel Lebeda, Simon Hadfield, Richard Bowden
Abstract:
Although 3D reconstruction from a monocular video has been an active area of research for a long time, and the resulting models offer great realism and accuracy, strong conditions must be typically met when capturing the video to make this possible. This prevents general reconstruction of moving objects in dynamic, uncontrolled scenes. In this paper, we address this issue. We present a novel algorithm for modelling 3D shapes from unstructured, unconstrained discontinuous footage. The technique is robust against distractors in the scene, background clutter and even shot cuts. We show reconstructed models of objects, which could not be modelled by conventional Structure from Motion methods without additional input. Finally, we present results of our reconstruction in the presence of shot cuts, showing the strength of our technique at modelling from existing footage.
Reference:
Dense Rigid Reconstruction from Unstructured Discontinuous Video (Karel Lebeda, Simon Hadfield, Richard Bowden), In Proceedings of the International Conference on Computer Vision workshop on 3D Representation and Recognition, IEEE, 2015. (Oral, Slides, Supplementary Results)
Bibtex Entry:
@InProceedings{Lebeda15b,
  Title                    = {Dense Rigid Reconstruction from Unstructured Discontinuous Video},
  Author                   = {Karel Lebeda and Simon Hadfield and Richard Bowden},
  Booktitle                = {Proceedings of the International Conference on Computer Vision workshop on 3D Representation and Recognition},
  Year                     = {2015},

  Address                  = {Santiago, Chile},
  Month                    = {17} # dec,
  Organization             = {IEEE},
  Publisher                = {IEEE},
  Pages = {814 -- 822},
  Doi = {10.1109/ICCVW.2015.110},
  Gsid = {673827947303576949},
  Comment                  = {<font color="red">Oral</font>, <a href="http://cvssp.org/Personal/KarelLebeda/papers/3dRR2015_pres.zip">Slides</a>, <a href="http://cvssp.org/Personal/KarelLebeda/TMAGIC/dense/">Supplementary Results</a>},
  Crossref                 = {ICCV15},
  Url                      = {http://personal.ee.surrey.ac.uk/Personal/S.Hadfield/papers/Dense%20Rigid%20Reconstruction%20from%20Unstructured%20Discontinuous%20Video.pdf},
  Abstract = {Although 3D reconstruction from a monocular video has been an active area of research for a long time, and the resulting models offer great realism and accuracy, strong conditions must be typically met when capturing the video to make this possible. This prevents general reconstruction of moving objects in dynamic, uncontrolled scenes. In this paper, we address this issue. We present a novel algorithm for modelling 3D shapes from unstructured, unconstrained discontinuous footage. The technique is robust against distractors in the scene, background clutter and even shot cuts. We show reconstructed models of objects, which could not be modelled by conventional Structure from Motion methods without additional input. Finally, we present results of our reconstruction in the presence of shot cuts, showing the strength of our technique at modelling from existing footage.}
}
Powered by bibtexbrowser