Improved 2D-to-3D video conversion by fusing optical flow analysis and scene depth learning

Herrera Conejero, José Luis and Blanco Adán, Carlos Roberto del and García Santos, Narciso (2016). Improved 2D-to-3D video conversion by fusing optical flow analysis and scene depth learning. In: "DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON)", 04/07/2016 - 06/07/2016, Hamburg, Germany. pp. 1-4. https://doi.org/10.1109/3DTV.2016.7548954.

Description

Title: Improved 2D-to-3D video conversion by fusing optical flow analysis and scene depth learning
Author/s:
  • Herrera Conejero, José Luis
  • Blanco Adán, Carlos Roberto del
  • García Santos, Narciso
Item Type: Presentation at Congress or Conference (Article)
Event Title: DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON)
Event Dates: 04/07/2016 - 06/07/2016
Event Location: Hamburg, Germany
Title of Book: DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON)
Date: 2016
Subjects:
Freetext Keywords: 2D-to-3D conversion, depth maps, depth prior, clustering, machine learning
Faculty: E.T.S.I. Telecomunicación (UPM)
Department: Señales, Sistemas y Radiocomunicaciones
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

Abstract: Automatic 2D-to-3D conversion aims to reduce the existing gap between the scarce 3D content and the incremental amount of displays that can reproduce this 3D content. Here, we present an automatic 2D-to-3D conversion algorithm that extends the functionality of the most of the existing machine learning based conversion approaches to deal with moving objects in the scene, and not only with static backgrounds. Under the assumption that images with a high similarity in color have likely a similar 3D structure, the depth of a query video sequence is inferred from a color + depth training database. First, a depth estimation for the background of each image of the query video is computed adaptively by combining the depths of the most similar images to the query ones. Then, the use of optical flow enhances the depth estimation of the different moving objects in the foreground. Promising results have been obtained in a public and widely used database.

Funding Projects

TypeCodeAcronymLeaderTitle
Government of SpainTEC2013- 48453MR-UHDTVMinisterio de Economa y CompetitividadUnspecified

More information

Item ID: 46721
DC Identifier: http://oa.upm.es/46721/
OAI Identifier: oai:oa.upm.es:46721
DOI: 10.1109/3DTV.2016.7548954
Official URL: http://ieeexplore.ieee.org/document/7548954/
Deposited by: Memoria Investigacion
Deposited on: 19 Jun 2017 16:58
Last Modified: 19 Jun 2017 16:58
  • 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