DocumentCode :
631924
Title :
Parallel implementation of depth-image-based rendering
Author :
Kun Xu ; Xiangyang Ji ; Ruiping Wang ; Qionghai Dai
Author_Institution :
Dept. of Autom., Tsinghua Univ., Beijing, China
fYear :
2011
fDate :
7-8 Dec. 2011
Firstpage :
1
Lastpage :
4
Abstract :
Depth-image-based rendering (DIBR) is a key step in 3D video generation. Parallel implementation of DIBR is able to improve rendering efficiency. General DIBR algorithms include two steps: pixel shifting (warping) and hole filling. There are memory correlations in these steps. To minimize memory conflict, we employ an auxiliary matrix to record maximum shifting distance. Implementation details on OpenMP and CUDA are presented and experimental results on GPU and multi-core CPU are compared.
Keywords :
rendering (computer graphics); video signal processing; 3D video generation; CUDA; DIBR; GPU; OpenMP; auxiliary matrix; depth image based rendering; hole filling; maximum shifting distance; memory conflict; multicore CPU; pixel shifting; warping; Abstracts; Algorithm design and analysis; Digital TV; Image resolution; DIBR; hole-filling; parallel computation; pixel shifting;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
3D Imaging (IC3D), 2011 International Conference on
Conference_Location :
Liege
Print_ISBN :
978-1-4799-1577-4
Type :
conf
DOI :
10.1109/IC3D.2011.6584366
Filename :
6584366
Link To Document :
بازگشت