Complexity Reduction of ANN Model for CU Size Selection in HEVC

Mateusz Lorkiewicz, Olgierd Stankiewicz, Marek Domanski, Hsueh Ming Hang, Wen Hsiao Peng

研究成果: Conference contribution同行評審

1 引文 斯高帕斯(Scopus)

摘要

In HEVC compression is performed in Coding Units (CUs) being pixel blocks of a size adaptively chosen according to the local content within a video frame. Nearoptimum selection of the frame partition into CUs is crucial for the coding efficiency. A huge number of partitioning schemes is available and the optimum partitioning scheme is obtained in an iterative computation-heavy procedure in a classic HEVC encoder. In order to reduce the encoding time and the encoding energy, a few approaches have been proposed with the use of neural networks (NNs). These approaches demonstrate a significant reduction of the encoding time and a negligible increase of the bitrate as compared to the traditional iterative approach. Nevertheless, they use very large neural networks whereas it is demonstrated in this paper that much smaller neural networks provide similar results encoding tome reduction with the similar bitrate reduction.

原文English
主出版物標題2023 Signal Processing Symposium, SPSympo 2023
發行者Institute of Electrical and Electronics Engineers Inc.
頁面111-116
頁數6
ISBN(電子)9788395602078
DOIs
出版狀態Published - 2023
事件2023 Signal Processing Symposium, SPSympo 2023 - Karpacz, Poland
持續時間: 26 9月 202328 9月 2023

出版系列

名字2023 Signal Processing Symposium, SPSympo 2023

Conference

Conference2023 Signal Processing Symposium, SPSympo 2023
國家/地區Poland
城市Karpacz
期間26/09/2328/09/23

指紋

深入研究「Complexity Reduction of ANN Model for CU Size Selection in HEVC」主題。共同形成了獨特的指紋。

引用此