3D+t Reconstruction in the Context of Locally Spheric Shaped Data Observation

Abstract : The main focus of this paper is 3D+t shape recovery from 3D spatial data and 2D+t temporal sequences. This reconstruction is particularly challenging due to the great deal of in-depth information loss observed on the 2D+t temporal sequence. Our approach embed a geometrical local constraint to handle the critical lack of information. This prior constraint is defined by a spherical topology because several applications may be concerned. It allows us to model relevantly the 3D- to-2D transformation that reduces each 3D image into a 2D frame. We then can build a 3D inaccurate inverse reconstruction of each 2D frame belonging to the video, i.e. 2D+t sequence. These inaccurate 3D images are enhanced by gradual motion compensation using a regularity criterion. Results on synthetic data are displayed.
Document type :
Conference papers
Complete list of metadatas

https://hal.inria.fr/inria-00635911
Contributor : Nathalie Gaudechoux <>
Submitted on : Wednesday, October 26, 2011 - 11:58:08 AM
Last modification on : Thursday, March 21, 2019 - 2:42:11 PM

Links full text

Identifiers

Citation

Wafa Rekik, Dominique Béréziat, Séverine Dubuisson. 3D+t Reconstruction in the Context of Locally Spheric Shaped Data Observation. CAIP 2007 - 12th International Conference on Computer Analysis of Images and Patterns, Aug 2007, Vienna, Austria. pp.482-489, ⟨10.1007/978-3-540-74272-2_60⟩. ⟨inria-00635911⟩

Share

Metrics

Record views

305