Accelerate CU Partition in HEVC using Large-Scale Convolutional Neural Network

TL;DR

This paper introduces a CNN-based two-stage approach with an early-termination mechanism to accelerate CU partitioning in HEVC intra-mode, significantly reducing encoding time with minimal bitrate impact.

Contribution

It presents a novel two-stage CNN method combined with an early-termination mechanism to efficiently decide CU partitions in HEVC intra-mode.

Findings

Achieves about 37% average encoding time reduction.

Maintains negligible BD-Bitrate increase.

Effectively filters homogeneous CUs to reduce computation.

Abstract

High efficiency video coding (HEVC) suffers high encoding computational complexity, partly attributed to the rate-distortion optimization quad-tree search in CU partition decision. Therefore, we propose a novel two-stage CU partition decision approach in HEVC intra-mode. In the proposed approach, CNN-based algorithm is designed to decide CU partition mode precisely in three depths. In order to alleviate computational complexity further, an auxiliary earl-termination mechanism is also proposed to filter obvious homogeneous CUs out of the subsequent CNN-based algorithm. Experimental results show that the proposed approach achieves about 37% encoding time saving on average and insignificant BD-Bitrate rise compared with the original HEVC encoder.