30 September 2016 Rapid learning-based video stereolization using graphic processing unit acceleration
Author Affiliations +
Abstract
Video stereolization has received much attention in recent years due to the lack of stereoscopic three-dimensional (3-D) contents. Although video stereolization can enrich stereoscopic 3-D contents, it is hard to achieve automatic two-dimensional-to-3-D conversion with less computational cost. We proposed rapid learning-based video stereolization using a graphic processing unit (GPU) acceleration. We first generated an initial depth map based on learning from examples. Then, we refined the depth map using saliency and cross-bilateral filtering to make object boundaries clear. Finally, we performed depth-image-based-rendering to generate stereoscopic 3-D views. To accelerate the computation of video stereolization, we provided a parallelizable hybrid GPU–central processing unit (CPU) solution to be suitable for running on GPU. Experimental results demonstrate that the proposed method is nearly 180 times faster than CPU-based processing and achieves a good performance comparable to the-state-of-the-art ones.
© 2016 SPIE and IS&T
Tian Sun, Tian Sun, Cheolkon Jung, Cheolkon Jung, Lei Wang, Lei Wang, Joongkyu Kim, Joongkyu Kim, } "Rapid learning-based video stereolization using graphic processing unit acceleration," Journal of Electronic Imaging 25(5), 053021 (30 September 2016). https://doi.org/10.1117/1.JEI.25.5.053021 . Submission:
JOURNAL ARTICLE
9 PAGES


SHARE
RELATED CONTENT

Scalable hierarchical video summary and search
Proceedings of SPIE (December 31 2000)
Video transcoding using GPU accelerated decoder
Proceedings of SPIE (January 25 2011)
Image processing on parallel GPU pixel units
Proceedings of SPIE (February 01 2006)
GPU-completeness: theory and implications
Proceedings of SPIE (January 25 2011)

Back to Top