Memorias de investigación
Communications at congresses:
Learning 3D Structure from 2D Images Using LBP Features
Year:2014
Research Areas
  • Electronic technology and of the communications
Information
Abstract
An automatic machine learning strategy for computing the 3D structure of monocular images from a single image query using Local Binary Patterns is presented. The 3D structure is inferred through a training set composed by a repository of color and depth images, assuming that images with similar structure present similar depth maps. Local Binary Patterns are used to characterize the structure of the color images. The depth maps of those color images with a similar structure to the query image are adaptively combined and filtered to estimate the final depth map. Using public databases, promising results have been obtained outperforming other state-of-the-art algorithms and with a computational cost similar to the most efficient 2D-to-3D algorithms.
International
Si
Congress
IEEE Int. Conf. on Image Processing, ICIP 2014
960
Place
Paris, France
Reviewers
Si
ISBN/ISSN
1522-4880
10.1109/ICIP.2014.7025405
Start Date
27/10/2014
End Date
30/10/2014
From page
2022
To page
2025
Learning 3D Structure from 2D Images Using LBP Features
Participants
Research Group, Departaments and Institutes related
  • Creador: Grupo de Investigación: Grupo de Tratamiento de Imágenes (GTI)
  • Departamento: Señales, Sistemas y Radiocomunicaciones