The rich choice of hierarchical partitioning modes within the coding tree unit (CTU) in the high efficiency video coding (HEVC/H.265) standard is the main reason for its higher coding efficiency, as well as its high computational complexity. The single most timing consuming process in H.265/HEVC is motion estimation (ME). In this paper, to accelerate the ME process, we propose an efficient parallel algorithm by exploiting inter-pixel similarity. The result shows with less than 1% bitrate increases ME can be accelerated by up to 5.7 times. To further enhance the encoder performance, we propose a novel strategy that employs quantization parameter as the indicator to early-terminate the coding. Overall encoding time is improved by up to 3.5 times, with a less than 6% increase in the bitrate.

This paper investigates the problem of MVC from a high-level perspective and proposes a multiple-view-frame-parallel (MVFP), scheduling scheme for a computing cluster. The proposed scheme outperforms the view sequential coding by a factor of more than 12, for the IPP prediction structure for MVC.

In this paper, we propose a novel massively parallel motion estimation for HEVC using an efficient yet flexible predicate algorithm, ScalingFast that exploits inter-pixel similarities. When evaluated over four video test video sequences with changing resolution, the proposed algorithm outperforms the anchor algorithm by factor of up to 4.6, with little to no loss in rate-distortion (RD) performance.

The challenge to H.265/HEVC multiview video coding (MVC) is its extremely high computational complexity. This paper presents the development and implementation of a scalable massively parallel fast search algorithm to significantly reduce the computational cost of motion and disparity estimation over the current best available GPU full block matching and sub optimal CPU fast search algorithms by a factor up to 2.4 and 8.4, respectively.

Multiview video coding (MVC) has recently received considerable attention. It is proposed as an extension of H.264/Advanced Video Coding (AVC) standard for multiple video source compression. To resolve the extremely high computational complexity of MVC (and in fact other AVC techniques), suitable parallel algorithms need to be developed that are amenable to implementation on low-cost massively parallel architecture, platforms that have found a common place due to recent advances in the parallel computer architecture. The high complexity of MVC is due to its prediction structure, where motion estimation (ME) between the frames and disparity estimation (DE) between the views contribute to more than 99% of overall complexity of the coder. This paper presents the development and implementation of a scalable massively parallel fast search algorithm to significantly reduce the computational cost of ME/DE over the current best available full block matching, and suboptimal fast search algorithms. The proposed massively parallel fast search algorithm (DZfast), when evaluated over eight views, outperforms the existing full search and fast search MVC algorithms by a factor of up to 245.8 and 8.4, respectively. This speedup comes at no or minute loss in rate-distortion performance.

This paper presents the use of a computer cluster with heterogeneous computing components to provide concurrency and multi-level parallelism at coarse grain and massive fine-grain for multiview video coding (MVC) applications. MVC involves coding of multiple video sequences that are taken from the same scene but different perspective. In addition to motion estimation (ME) used in conventional video coding for single view video for exploiting inter-frame temporal similarities, MVC adopts disparity estimation (DE) to further increase compression. To overcome the huge computational cost associated with ME and by extension with DE, attention has been mainly focused on developing fast ME/DE algorithms. Although fast ME/DE algorithms bring substantial speedup, to achieve realtime MVC encoding, it requires further acceleration of the coding process at higher levels. Towards this end, this paper proposes a multiple-view-parallel, multiple-interleaved group of pictures (multiple-IGOP) scheduling scheme for MVC. When evaluated over eight views, with no loss in rate distortion (RD) performance, the proposed scheme outperforms view-sequential coding by a factor of up to 12.4 and 12.3, respectively, for two popular prediction structures, IBP and IPP.

Multiview video coding (MVC) is an extension of H.264/AVC standard. Its purpose is to further increase compression efficiency when multiple video sources are presented for coding. The computational complexity of MVC, however, is extremely high due to the motion estimation (ME) between the frames and disparity estimation (DE) between the views, contributing to more than 99% of overall complexity of the coder. For MVC to find a common place for real-time applications requires acceleration of ME and DE engines. On the other hand, there is a recent uptake of graphical processing unit (GPU) computing to significantly enhance the performance of signal and image processing applications, through massive-parallel processing. This paper presents the development and GPU implementation of a parallel full search algorithm to significantly reduce the computational complexity of ME and DE over the full search and TZsearch estimations on a sequential processor, by a factor of 300 and 4, respectively.