发明名称 Method and system for processing multiview videos for view synthesis using skip and direct modes
摘要 Multiview videos are acquired by overlapping cameras. Side information is used to synthesize multiview videos. A reference picture list is maintained for current frames of the multiview videos, the reference picture indexes temporal reference pictures and spatial reference pictures of the acquired multiview videos and the synthesized reference pictures of the synthesized multiview video. Each current frame of the multiview videos is predicted according to reference pictures indexed by the associated reference picture list with a skip mode and a direct mode, whereby the side information is inferred from the synthesized reference picture. Alternatively, the depth images corresponding to the multiview videos of the input data, and this data are encoded as part of the bitstream depending on a SKIP type.
申请公布号 US8854486(B2) 申请公布日期 2014.10.07
申请号 US201113299195 申请日期 2011.11.17
申请人 Mitsubishi Electric Research Laboratories, Inc. 发明人 Tian Dong;Cheung Ngai-Man;Vetro Anthony
分类号 H04N5/225;H04N13/02;H04N7/12;H04N19/122;H04N19/174;H04N7/18;H04N19/61;H04N19/597;H04N19/105;H04N19/176;H04N19/423;H04N19/51;H04N19/577;H04N19/27;H04N19/159;H04N19/70;H04N19/172;H04N19/63;H04N19/635;H04N19/132;H04N19/615;H04N19/46;H04N19/14;H04N19/147;H04N19/54;H04N19/13 主分类号 H04N5/225
代理机构 代理人 Brinkman Dirk;Vinokur Gene
主权项 1. A method for processing a plurality of multiview videos of a scene, in which each video is acquired by a corresponding camera arranged at a particular pose, and in which a view of each camera overlaps with the view of at least one other camera, comprising the steps of: obtaining side information for synthesizing a particular view of multiview video; synthesizing a synthesized multiview video from the plurality of multiview videos and the side information; maintaining a reference picture list for each current frame of each of the plurality of multiview videos, the reference picture list indexing temporal reference it pictures and spatial reference pictures of the plurality of acquired multiview videos and synthesized reference pictures of the synthesized multiview video; and predicting each current frame of the plurality of multiview videos according to reference pictures indexed by the associated reference picture list with an adaptive-reference skip mode or an adaptive-reference direct mode, wherein the adaptive-reference skip mode and adaptive-reference direct mode use one of the plurality of reference pictures.
地址 Cambridge MA US