| 摘要 |
<P>PROBLEM TO BE SOLVED: To provide systems and methods for synthesizing a detailed depth map from a video image. <P>SOLUTION: The method for synthesizing the detailed depth map from the video image includes the steps of: using motion vectors correlated to pixels to group the image into regions; defining a border region between the regions; generating a coarse depth map by a step to assign depth values to the regions and by a step to assign depth values to pixels in the border region; computing gradient information using edge information from the image and a gradient map derived from the coarse depth map; and obtaining the depth map by applying a surface reconstruction technique for surface gradient integration to the gradient information. <P>COPYRIGHT: (C)2010,JPO&INPIT |
