Accelerating Image-Domain-Warping Virtual View Synthesis on GPGPU

作者：Wang, Ronggang^*; Luo, Jiajia; Jiang, Xiubao; Wang, Zhenyu; Wang, Wenmin; Li, Ge; Gao, Wen

来源：IEEE Transactions on Multimedia, 2017, 19(6): 1392-1400.

DOI：10.1109/TMM.2017.2654120

• General-purpose computing on a graphics processing unit (GPGPU)
• image-domain-warping (IDW)
• real-time
• stereo 3D (S3D) to N-view
• virtual view synthesis

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 + GPU (NVIDIA GTX980) platform.

• 出版日期2017-6
• 单位北京大学深圳研究生院