ECCV 2012 – Shape from Angle Regularity

Aamer Zaheer, Maheen Rashid, Sohaib Khan
European Conference on Computer Vision (ECCV), Florence, Italy, October 7-13, 2012

Abstract

This paper deals with automatic Single View Reconstruction (SVR) of multi-planar scenes characterized by a profusion of straight lines and mutually orthogonal line-pairs. We provide a new shape-from-X constraint based on this regularity of angles between line-pairs in man- made scenes. First, we show how the presence of such regular angles can be used for 2D rectification of an image of a plane. Further, we pro- pose an automatic SVR method assuming there are enough orthogonal line-pairs available on each plane. This angle regularity is only imposed on physically intersecting line-pairs, making it a local constraint. Unlike earlier literature, our approach does not make restrictive assumptions about the orientation of the planes or the camera and works for both in- door and outdoor scenes. Results are shown on challenging images which would be difficult to reconstruct for existing automatic SVR algorithms.

Resources

Download PDF
(Distributed here for timely dissemination of scholarly work. Copyright retained by copyright holders. May not be posted without permission from copyright holders.)

Download Code

Text Reference:

Aamer Zaheer, Maheen Rashid, Sohaib Khan, 
"Shape from Angle Regularity",
in Proceedings of the 12th European Conference on Computer Vision, ECCV, October 2012

Bibtex Reference:

@inproceedings{ShapeFromAngleRegularity2012,
   author = "Aamer Zaheer and Maheen Rashid and Sohaib Khan",
   title = "Shape From Angle Regularity",
   booktitle = "Proceedings of the 12th European Conference on Computer Vision",
   month = "October",
   year = "2012",
}