Free Viewpoint TV and 3D Video View Synthesis Using Spatio-temporal Information

• Main Authors: Li-Chung Huang, 黃利中
• Other Authors: Jin-Jang Leou
• Format: Others
• Language: en_US
• Published: 2015
• Online Access: http://ndltd.ncl.edu.tw/handle/30189620236656593898

碩士 === 國立中正大學 === 資訊工程研究所 === 103 === To reduce the transmission bitrate, virtual view synthesis is an important technique for three-dimensional television (3DTV) and free viewpoint television (FTV) applications. The main aim of virtual view synthesis is to synthesize the virtual view sequence of some viewpoint from multi-view video plus depth sequences taken by cameras. In this study, virtual view synthesis approach for multi-view video plus depth sequences taken by non-parallel cameras using spatio-temporal information are proposed. Using spatial information, modified adaptive median filtering, weight computation, 3D warping, blending, and modified inpainting are employed in the proposed approach, whereas using temporal information, including the techniques employed in the proposed approach using spatial information, motion estimation and compensation, “temporal” fusion, and “temporal” refinement are also employed in the proposed approach. Based on the experimental results obtained in this study, the synthesis virtual view quality of the proposed approach are better than those of the three comparison approaches.