Ensemble Learning for Efficient VVC Bitrate Ladder Prediction

TL;DR

This paper introduces an ensemble machine learning approach to predict optimal video resolution and bitrate ladders for VVC encoding, achieving significant bitrate savings and complexity reduction with minimal efficiency loss.

Contribution

It presents a novel ensemble learning scheme that predicts bitrate ladders with minimal encoding passes, balancing performance and computational complexity.

Findings

Achieves 13% bitrate reduction over static ladders.

Reduces complexity by 86-92% compared to fully specialized methods.

Maintains less than 1% coding efficiency loss.

Abstract

Changing the encoding parameters, in particular the video resolution, is a common practice before transcoding. To this end, streaming and broadcast platforms benefit from so-called bitrate ladders to determine the optimal resolution for given bitrates. However, the task of determining the bitrate ladder can usually be challenging as, on one hand, so-called fit-for-all static ladders would waste bandwidth, and on the other hand, fully specialized ladders are often not affordable in terms of computational complexity. In this paper, we propose an ML-based scheme for predicting the bitrate ladder based on the content of the video. The baseline of our solution predicts the bitrate ladder using two constituent methods, which require no encoding passes. To further enhance the performance of the constituent methods, we integrate a conditional ensemble method to aggregate their decisions, with a negligibly limited number of encoding passes. The experiment, carried out on the optimized software encoder implementation of the VVC standard, called VVenC, shows significant performance improvement. When compared to static bitrate ladder, the proposed method can offer about 13% bitrate reduction in terms of BD-BR with a negligible additional computational overhead. Conversely, when compared to the fully specialized bitrate ladder method, the proposed method can offer about 86% to 92% complexity reduction, at cost the of only 0.8% to 0.9% coding efficiency drop in terms of BD-BR.