Globally Optimal Spatio-temporal Reconstruction from Cluttered Videos - École des Ponts ParisTech
Conference Papers COMPUTER VISION - ACCV 2009, PT III Year : 2010

Globally Optimal Spatio-temporal Reconstruction from Cluttered Videos

Abstract

We propose a method for multi-view reconstruction from videos adapted to dynamic cluttered scenes under uncontrolled imaging conditions. Taking visibility into account, and being based on a global optimization of a true spatio-temporal energy, it oilers several desirable properties: no need for silhouettes, robustness to noise, independent from any initialization, no heuristic force, reduced flickering results, etc. Results on real-world data proves the potential of what is, to our knowledge, the only globally optimal spatio-temporal multi-view reconstruction method.
Fichier principal
Vignette du fichier
ACCV09e.pdf (459.76 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-00711066 , version 1 (02-07-2012)

Identifiers

Cite

Ehsan Aganj, Jean-Philippe Pons, Renaud Keriven. Globally Optimal Spatio-temporal Reconstruction from Cluttered Videos. ACCV 2009 9th Asian conference on Computer Vision, Sep 2009, Xi'an, China. pp.667-678, ⟨10.1007/978-3-642-12297-2_64⟩. ⟨hal-00711066⟩
170 View
218 Download

Altmetric

Share

More