Real-time free-viewpoint DIBR on GPUs for large base-line multi-view 3DTV videos

Q.L. Do, G. Bravo, S. Zinger, P.H.N. With, de

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

8 Citations (Scopus)

Abstract

GPUs are ample utilized for their parallel processing capabilities and are also interesting in the area of 3D image processing where computational demanding tasks are essential. We concentrate particularly on free-view 3DTV applications, based on image warping to the new view and image artifact reduction techniques. In this paper, we report on the implementation of an efficient free-viewpoint DIBR algorithm with an off-the-shelf GPU, which can be readily integrated into future 3DTV systems. For exploiting maximal parallelism, we have mapped the processing of each pixel to a separate thread and grouped multiple threads to larger blocks as much as possible. Using a combination of the highly parallel programming architecture CUDA and a graphics API, we have achieved a real-time performance operating on 1080p HD multi-view video with a rendering quality that is comparable to the software implementation.
Original languageEnglish
Title of host publicationProceedings of the IEEE Visual Communications and Image Processing Conference 2011 (VCIP), 6-9- November, 2011, Taiwan
PublisherInstitute of Electrical and Electronics Engineers
Pages1301-1304
ISBN (Print)978-1-4577-1321-7
DOIs
Publication statusPublished - 2011
EventVisual Communications and Image Processing 2011 (VCIP 2011), November 6-9, 2011, Tainan, Taiwan - Y. S. Sun Green Building Research Center, Tainan, Taiwan
Duration: 6 Nov 20119 Nov 2011
http://conf.ncku.edu.tw/vcip2011/

Conference

ConferenceVisual Communications and Image Processing 2011 (VCIP 2011), November 6-9, 2011, Tainan, Taiwan
Abbreviated titleVCIP 2011
CountryTaiwan
CityTainan
Period6/11/119/11/11
Other"A Moment of Inheritance and Escalation"
Internet address

Fingerprint

Dive into the research topics of 'Real-time free-viewpoint DIBR on GPUs for large base-line multi-view 3DTV videos'. Together they form a unique fingerprint.

Cite this