iCUS-Intelligent CU Size Selection for HEVC Inter Prediction.pdf (3.54 MB)
Download file

iCUS: Intelligent CU Size Selection for HEVC Inter Prediction

Download (3.54 MB)
journal contribution
posted on 25.02.2022, 10:31 by Buddhiprabha Erabadda, Thanuja MallikarachchiThanuja Mallikarachchi, Gosala Kulupana, Anil Fernando
The hierarchical quadtree partitioning of Coding Tree Units (CTU) is one of the striking features in HEVC that contributes towards its superior coding performance over its predecessors. However, the brute force evaluation of the quadtree hierarchy using the Rate-Distortion (RD) optimisation, to determine the best partitioning structure for a given content, makes it one of the most time-consuming operations in HEVC encoding. In this context, this paper proposes an intelligent fast Coding Unit (CU) size selection algorithm to expedite the encoding process of HEVC inter-prediction. The proposed algorithm introduces (i) two CU split likelihood modelling and classification approaches using Support Vector Machines (SVM) and Bayesian probabilistic models, and (ii) a fast CU selection algorithm that makes use of both offline trained SVMs and online trained Bayesian probabilistic models. Finally, (iii) a computational complexity to coding efficiency trade-off mechanism is introduced to flexibly control the algorithm to suit different encoding requirements. The experimental results of the proposed algorithm demonstrate an average encoding time reduction performance of 53.46%, 61.15%, and 58.15% for Low Delay B , Random Access , and Low Delay P configurations, respectively, with Bjøntegaard Delta-Bit Rate (BD-BR) losses of 2.35%, 2.9%, and 2.35%, respectively, when evaluated across a wide range of content types and quality levels


Cardiff Metropolitan University (Grant ID: Cardiff Metropolian (Internal))


Published in

IEEE Access




VoR (Version of Record)


Erabadda, B., Mallikarachchi, T., Kulupana, G. and Fernando, A. (2020) 'iCUS: Intelligent CU Size Selection for HEVC Inter Prediction', IEEE Access, 8, pp.141143-141158.

Electronic ISSN


Cardiff Met Affiliation

  • Cardiff School of Technologies

Cardiff Met Authors


Copyright Holder

© The Authors



Usage metrics

Read the peer-reviewed publication