A distributed video coding system for multi view video plus depth

摘要: Multi-view video plus depth (MVD) is gathering huge attention, as witnessed by the recent standardization activity, since its rich information about geometry of scene allows high-quality synthesis virtual viewpoints. Distributed coding such kind content a challenging problem whose solution could enable new services interactive multi-view streaming. In this work we propose to exploit geometrical MVD format in order estimate inter-view occlusions without communication among cameras. Experimental results show bit rate reduction up 77% for low w.r.t. state-of-the-art architectures.