Machine learning for video compression: Macroblock mode decision

Video compression currently is dominated by engineering and fine-tuned heuristic methods. In this paper, we propose to instead apply the well-developed machinery of machine learning in order to support the optimization of existing video encoders and the creation of new ones. Exemplarily, we show how by machine learning we can improve one encoding step that is crucial for the performance of all current video standards: macroblock mode decision. By formulating the problem in a Bayesian setup, we show that macroblock mode decision can be reduced to a classification problem with a cost function for misclassification that is sample dependent. We demonstrate how to apply different machine learning techniques to obtain suitable classifiers and we show in detailed experiments that all of these perform better than the state-of-the-art heuristic method