| 摘要 |
A method for forming a stereoscopic image from a main image of a scene captured from a main image viewpoint including one or more foreground objects, together a main image range map and a background image. A first-eye image is determined corresponding to a first-eye viewpoint and a second-eye image is determined corresponding to a second-eye viewpoint. At least one of the first-eye image and the second-eye image is determined by warping the main image to the associated viewpoint, wherein the warped main image includes one or more holes corresponding to scene content that was occluded in the main image; warping the background image to the associated viewpoint; and determining pixel values to fill the one or more holes in the warped main image using pixel values at corresponding pixel locations in the warped background image; and forming a stereoscopic image including the first-eye image and the second-eye image.
|
