QTMT‐LNN: A fast intra CU partition using lightweight neural network for 360‐degree video coding on VVC

Abstract

In the newest generation of video coding standard, Versatile Video Coding (VVC), a new technique called Quad Tree with nested Multi‐type Tree (QTMT) structure is introduced. QTMT significantly improves the coding efficiency, but the improvement in compression performance comes at the cost of drastically increased complexity. This paper proposes a fast intra partition algorithm using Lightweight Neural Network (LNN) to skip QTMT partition steps which are unlikely to be chosen as the best split modes. Specifically, five LNNs (for five QTMT split modes) are trained, using features that consider the characteristic of 360‐degree videos. The experimental results demonstrate that the proposed QTMT‐LNN can reduce the encoding time from 52.28% to 72.17% on average, with coding efficiency losses ranging from 0.71% to 1.78%. Compared to other fast algorithms for intra coding unit (CU) partition, the method outperforms the related works in terms of Bjontegaard delta bit‐rate (BDBR) and encoding time reduction.

Coding Tree Unit Partition Prediction Algorithm Utilizing Residual AttentionBased Long Short-Term Memory for Video Intra Coding

“…By considering VVC and HEVC, the HEVC takes a quad-tree-based CU recursive partition technique for CU [5]. The VVC utilizes quad-tree architecture as well as bi and trinomial tree partition architectures for better CU partition that made the complexity of intra-frame coding averagely 18 times greater than HEVC [6,7]. Utilizing deep learning-based acceleration methods, both encoders demanding support from graphical processing units (GPUs) and diverse hardware GPUs aiding HEVC and VVC are enhanced [8].…”