Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/127278
Title: Accelerating Image-Domain-Warping Virtual View Synthesis on GPGPU
Authors: Ronggang Wang;Jiajia Luo;Xiubao Jiang;Zhenyu Wang;Wenmin Wang;Ge Li;Wen Gao
Year: 2017
Publisher: IEEE
Abstract: The image-domain-warping (IDW) method can effectively create high-quality virtual views. However, the IDW algorithm is very complex, and the software implementation for this method is far from real-time. In this paper, we propose an IDW-based view synthesis acceleration method on general-purpose computing on a graphics processing unit (GPGPU). Our method makes two main contributions. First, at the algorithm level, we employ FAST for sparse disparity estimation and adopt the successive over-relaxation iterative method to calculate warps. Second, at the platform level, two computation-intensive modules (data extraction and view synthesis) in IDW are offloaded to GPU using efficient data-level parallelism strategies. Experimental results demonstrate that our proposed acceleration method can speed up the original IDW algorithm by more than 110x, and HD stereo three-dimensional video can be converted to 8-view 4 K video (each view has an approximate 720P resolution) in real-time on a hybrid CPU &x002B; GPU (NVIDIA GTX980) platform.
URI: http://localhost/handle/Hannan/127278
volume: 19
issue: 6
More Information: 1392,
1400
Appears in Collections:2017

Files in This Item:
File SizeFormat 
7819453.pdf885.92 kBAdobe PDF
Title: Accelerating Image-Domain-Warping Virtual View Synthesis on GPGPU
Authors: Ronggang Wang;Jiajia Luo;Xiubao Jiang;Zhenyu Wang;Wenmin Wang;Ge Li;Wen Gao
Year: 2017
Publisher: IEEE
Abstract: The image-domain-warping (IDW) method can effectively create high-quality virtual views. However, the IDW algorithm is very complex, and the software implementation for this method is far from real-time. In this paper, we propose an IDW-based view synthesis acceleration method on general-purpose computing on a graphics processing unit (GPGPU). Our method makes two main contributions. First, at the algorithm level, we employ FAST for sparse disparity estimation and adopt the successive over-relaxation iterative method to calculate warps. Second, at the platform level, two computation-intensive modules (data extraction and view synthesis) in IDW are offloaded to GPU using efficient data-level parallelism strategies. Experimental results demonstrate that our proposed acceleration method can speed up the original IDW algorithm by more than 110x, and HD stereo three-dimensional video can be converted to 8-view 4 K video (each view has an approximate 720P resolution) in real-time on a hybrid CPU &x002B; GPU (NVIDIA GTX980) platform.
URI: http://localhost/handle/Hannan/127278
volume: 19
issue: 6
More Information: 1392,
1400
Appears in Collections:2017

Files in This Item:
File SizeFormat 
7819453.pdf885.92 kBAdobe PDF
Title: Accelerating Image-Domain-Warping Virtual View Synthesis on GPGPU
Authors: Ronggang Wang;Jiajia Luo;Xiubao Jiang;Zhenyu Wang;Wenmin Wang;Ge Li;Wen Gao
Year: 2017
Publisher: IEEE
Abstract: The image-domain-warping (IDW) method can effectively create high-quality virtual views. However, the IDW algorithm is very complex, and the software implementation for this method is far from real-time. In this paper, we propose an IDW-based view synthesis acceleration method on general-purpose computing on a graphics processing unit (GPGPU). Our method makes two main contributions. First, at the algorithm level, we employ FAST for sparse disparity estimation and adopt the successive over-relaxation iterative method to calculate warps. Second, at the platform level, two computation-intensive modules (data extraction and view synthesis) in IDW are offloaded to GPU using efficient data-level parallelism strategies. Experimental results demonstrate that our proposed acceleration method can speed up the original IDW algorithm by more than 110x, and HD stereo three-dimensional video can be converted to 8-view 4 K video (each view has an approximate 720P resolution) in real-time on a hybrid CPU &x002B; GPU (NVIDIA GTX980) platform.
URI: http://localhost/handle/Hannan/127278
volume: 19
issue: 6
More Information: 1392,
1400
Appears in Collections:2017

Files in This Item:
File SizeFormat 
7819453.pdf885.92 kBAdobe PDF