SVT-AV1 Encoding Bitrate Estimation Using Motion Search Information

TL;DR

This paper proposes a method to estimate video encoding bitrate accurately using motion search information combined with machine learning, enabling better encoding decisions and energy efficiency.

Contribution

It introduces a novel approach that leverages motion search data and Random Forests to predict encoded bitstream size with high correlation, improving bitrate estimation accuracy.

Findings

Pearson correlation above 0.96 between estimated and actual bitstream size.

Motion search errors correlate strongly with encoding bitrate.

Method enhances bitrate estimation for adaptive encoding strategies.

Abstract

Enabling high compression efficiency while keeping encoding energy consumption at a low level, requires prioritization of which videos need more sophisticated encoding techniques. However, the effects vary highly based on the content, and information on how good a video can be compressed is required. This can be measured by estimating the encoded bitstream size prior to encoding. We identified the errors between estimated motion vectors from Motion Search, an algorithm that predicts temporal changes in videos, correlates well to the encoded bitstream size. Combining Motion Search with Random Forests, the encoding bitrate can be estimated with a Pearson correlation of above 0.96.