Study of Compression Statistics and Prediction of Rate-Distortion Curves for Video Texture

TL;DR

This paper analyzes the spatio-temporal features of video textures and employs machine learning models to accurately predict rate-distortion curves, aiding faster encoding decisions in video compression.

Contribution

It introduces an exponential regression model that predicts rate-quality curves from texture features with high accuracy and low complexity.

Findings

Exponential model predicts rate-quality curves with 0.46% BDR accuracy.

Machine learning regression effectively models texture encoding statistics.

Results applicable to homogeneous video textures for improved encoding efficiency.

Abstract

Encoding textural content remains a challenge for current standardised video codecs. It is therefore beneficial to understand video textures in terms of both their spatio-temporal characteristics and their encoding statistics in order to optimize encoding performance. In this paper, we analyse the spatio-temporal features and statistics of video textures, explore the rate-quality performance of different texture types and investigate models to mathematically describe them. For all considered theoretical models, we employ machine-learning regression to predict the rate-quality curves based solely on selected spatio-temporal features extracted from uncompressed content. All experiments were performed on homogeneous video textures to ensure validity of the observations. The results of the regression indicate that using an exponential model we can more accurately predict the expected rate-quality curve (with a mean Bj{\o}ntegaard Delta rate of 0.46% over the considered dataset) while maintaining a low relative complexity. This is expected to be adopted by in the loop processes for faster encoding decisions such as rate-distortion optimisation, adaptive quantization, partitioning, etc.