4K-UHD real-time HEVC encoder with GPU accelerated motion estimation

Takano, Fumiyo; Igarashi, Hiroaki; Moriyoshi, Tatsuji

doi:10.1109/icip.2017.8296779

Cited by 7 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors saved 49ś52% of the encoding time at a 0.60ś0.88% BD-Rate increase. Another acceleration strategy is to oload the full inter prediction step, or a part of it, to a GPU [53,58,134] or an FPGA [10,12]. A comprehensive review by Zhang et al [164] covers literature on inter prediction of HEVC up to the year 2019.…”

Section: Computational Complexity Analysismentioning

confidence: 99%

“…Takano et al [134] proposed an HEVC encoder with an inter prediction (including transform and quantization of inter symbols) implemented on a GPU while the rest (intra prediction and entropy coding) is executed on a CPU. Instead of using neighboring blocks during the motion search, the authors separate the process into multiple layers with each layer reusing results from the previous one.…”

Section: Inter-frame Compressionmentioning

confidence: 99%

See 1 more Smart Citation

Image and Video Coding Techniques for Ultra-low Latency

et al. 2022

View full text Add to dashboard Cite

The next generation of wireless networks fosters the adoption of latency-critical applications such as XR, connected industry, or autonomous driving. This survey gathers implementation aspects of different image and video coding schemes and discusses their tradeoffs. Standardized video coding technologies such as HEVC or VVC provide a high compression ratio, but their enormous complexity sets the scene for alternative approaches like still image, mezzanine, or texture compression in scenarios with tight resource or latency constraints. Regardless of the coding scheme, we found inter-device memory transfers and the lack of sub-frame coding as limitations of current full-system and software-programmable implementations.

show abstract

Section: Computational Complexity Analysismentioning

confidence: 99%

Section: Inter-frame Compressionmentioning

confidence: 99%

Image and Video Coding Techniques for Ultra-low Latency

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Full search (FS) has generally been used in the area of parallel ME [26][27][28][29][30][31][32][33][34][35]. Since all the locations in the SR are searched in FS, s sr , the size of the SR, is the key parameter which determines the complexity.…”

Section: Motion Features For Adaptive Search Range Decisionmentioning

confidence: 99%

“…Nowadays, there have been many researches on implementing a parallel processing-based video encoder in order to achieve very high encoding performace [20][21][22][23][24][25][26][27][28][29][30][31][32][33][34][35]. One of them is to use a Graphics Processing Unit (GPU) for ME [26][27][28][29][30][31][32][33][34][35]. Since various search patterns are not preferable for parallel environment such as GPU due to both their irregular data flow and data dependency [8,14], they have generally adopt full search algorithm which searches all the points within a search range (SR).…”

Section: Introductionmentioning

confidence: 99%

Maximum A Posteriori Estimation-based Adaptive Search Range Decision for Accelerating HEVC Motion Estimation on GPU

2019

KSII TIIS

View full text Add to dashboard Cite

High Efficiency Video Coding (HEVC) suffers from high computational complexity due to its quad-tree structure in motion estimation (ME). This paper exposes an adaptive search range decision algorithm for accelerating HEVC integer-pel ME on GPU which estimates the optimal search range (SR) using a MAP (Maximum A Posteriori) estimator. There are three main contributions; First, we define the motion feature as the standard deviation of motion vector difference values in a CTU. Second, a MAP estimator is proposed, which theoretically estimates the motion feature of the current CTU using the motion feature of a temporally adjacent CTU and its SR without any data dependency. Thus, the SR for the current CTU is parallelly determined. Finally, the values of the prior distribution and the likelihood for each discretized motion feature are computed in advance and stored at a look-up table to further save the computational complexity. Experimental results show in conventional HEVC test sequences that the proposed algorithm can achieves high average time reductions without any subjective quality loss as well as with little BD-bitrate increase.

show abstract