Consistent view synthesis in interactive multiview imaging

An important question in the design of interactive multiview systems consists in determining the information needed by the decoder for high quality navigation between the views. Most of the existing techniques focus on the captured sequences and only consider their transmission, which does not guarantee consistency among receiver-generated frames of chosen virtual views. In this work, we propose a solution that additional transmits auxiliary information in order to help the construction of synthesized views, especially in the occluded areas. Comparative results with existing approaches validate this novel representation of multiview data for interactive navigation. We show that decoding quality and consistency among frames are improved with only a small share of additional information.