Complexity Reduction Study Based on RD Costs Approximation for VVC Intra Partitioning

TL;DR

This paper explores machine learning methods to reduce complexity in VVC intra partitioning by predicting RD costs and using RL to efficiently select coding unit splits, improving speed without sacrificing quality.

Contribution

Introduces size-independent ML approaches, including regression and RL with DQN, to predict RD costs and optimize intra partitioning in VVC, enhancing computational efficiency.

Findings

ML methods effectively predict RD costs for VVC.

RL approach accelerates partitioning decisions.

Proposed methods outperform traditional exhaustive search.

Abstract

In this paper, a complexity study is conducted for Versatile Video Codec (VVC) intra partitioning to accelerate the exhaustive search involved in Rate-Distortion Optimization (RDO) process. To address this problem, two main machine learning techniques are proposed and compared. Unlike existing methods, the proposed approaches are size independent and incorporate the Rate-Distortion (RD) costs of neighboring blocks as input features. The first method is a regression based technique that predicts normalized RD costs of a given Coding Unit (CU). As partitioning possesses the Markov property, the associated decision-making problem can be modeled as a Markov Decision Process (MDP) and solved by Reinforcement Learning (RL). The second approach is a RL agent learned from trajectories of CU decision across two depths with Deep Q-Network (DQN) algorithm. Then a pre-determined thresholds are applied for both methods to select a suitable split for the current CU.