Abstract
S ample Adaptive Offset (SAO) is a new component of in-loop filter in High Efficiency Video Coding (HEVC), the newest video coding standard. The SAO provides a superior image reconstruction quality at the cost of much higher computational complexity and it is more difficult to realize real-time coding when the image size is large, such as for high definition (HD) videos or ultra-HD videos. In this paper, we design the corresponding parallel algorithms for the SAO by exploiting GPU multi-core computing ability, including parallel computation of sample classification and statistics collection for each coding tree block (CTB), parallel calculation of the best offset values and minimum distortions for each class of edge offset (EO) and each band of band offset (BO), parallel processing of the SAO merging, and parallel implementation of SAO filtering. All the parallel algorithms are implemented on GPU programmed with CUDA language. Experimental results given in the paper show that, for HD video sequences, the parallel method can greatly improve the encoding efficiency of the SAO process with more than 22 times speedup while keeping the quality of reconstructed images unchanged, compared with the original serial algorithm implemented on CPU.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
