Fast 2D to 3D conversion using a clustering-based hierarchical search in a machine learning framework

Herrera Conejero, José Luis and Blanco Adán, Carlos Roberto del and García Santos, Narciso (2014). Fast 2D to 3D conversion using a clustering-based hierarchical search in a machine learning framework. In: "3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON)", 02/07/2014 - 04/07/2014, Budapest, Hungary. pp. 1-4.

Description

Title: Fast 2D to 3D conversion using a clustering-based hierarchical search in a machine learning framework
Author/s:
  • Herrera Conejero, José Luis
  • Blanco Adán, Carlos Roberto del
  • García Santos, Narciso
Item Type: Presentation at Congress or Conference (Article)
Event Title: 3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON)
Event Dates: 02/07/2014 - 04/07/2014
Event Location: Budapest, Hungary
Title of Book: 3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON)
Título de Revista/Publicación: 2014 3DTV-CONFERENCE: THE TRUE VISION - CAPTURE, TRANSMISSION AND DISPLAY OF 3D VIDEO (3DTV-CON)
Date: 2014
ISSN: 2161-2021
Subjects:
Freetext Keywords: 2D-to-3D conversion, fast conversion, 3D inference, machine learning, hierarchical search, SURF descriptors, database clustering
Faculty: E.T.S.I. Telecomunicación (UPM)
Department: Ingeniería de Sistemas Telemáticos [hasta 2014]
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (1MB) | Preview

Abstract

Automatic 2D-to-3D conversion is an important application for filling the gap between the increasing number of 3D displays and the still scant 3D content. However, existing approaches have an excessive computational cost that complicates its practical application. In this paper, a fast automatic 2D-to-3D conversion technique is proposed, which uses a machine learning framework to infer the 3D structure of a query color image from a training database with color and depth images. Assuming that photometrically similar images have analogous 3D structures, a depth map is estimated by searching the most similar color images in the database, and fusing the corresponding depth maps. Large databases are desirable to achieve better results, but the computational cost also increases. A clustering-based hierarchical search using compact SURF descriptors to characterize images is proposed to drastically reduce search times. A significant computational time improvement has been obtained regarding other state-of-the-art approaches, maintaining the quality results.

More information

Item ID: 36209
DC Identifier: http://oa.upm.es/36209/
OAI Identifier: oai:oa.upm.es:36209
Official URL: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6874736&pageNumber%3D136968
Deposited by: Memoria Investigacion
Deposited on: 05 Jul 2015 10:56
Last Modified: 05 Jul 2015 10:56
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM