Parallel processing for combined intra prediction in high efficiency video coding

Advanced intra prediction is one of the key components in highly efficient video coding since it reduces the bit-rate of the most costly intra frames. Combined Intra Prediction (CIP) is a novel tool that takes into account well established directional prediction from neighboring blocks, as well as local mean prediction from current block. In this way, it reduces bit-rate by further exploiting spatial redundancy. This paper proposes an implementation that will overcome its potential limitation limited parallelization capabilities. In order to make it more computationally parallelizable, adaptive open-loop prediction templates have been designed. Experiments have been performed which show that the proposed design preserves coding gains introduced by CIP, while providing a solution for more parallelizable, and therefore faster, implementations.