University of Bristol
University of Bristol
One of the challenges faced by many video providers is the heterogeneity of network specifications, user requirements, and content compression performance. The universal solution of a fixed bitrate ladder is inadequate in ensuring a high quality of user experience without re-buffering or introducing annoying compression artifacts. However, a content-tailored solution, based on extensively encoding across all resolutions and over a wide quality range is highly expensive in terms of computational, financial, and energy costs. Inspired by this, we propose approaches that exploit machine learning to predict a content-optimized bitrate ladder. The methods extract spatio-temporal features from the uncompressed content, train machine-learning models to predict the Pareto front parameters, and, based on that, build the ladder within a defined bitrate range. The methods have the benefit of significantly reducing the number of encodes required per sequence.
The collection of papers below provides all related research results.