| 摘要 |
The present invention relates to a device and method (100) of generating a depth map for an image using monocular information, the method comprising: generating (110) a first depth map for the image (205), wherein the first depth map corresponds with an estimate of a global depth profile of a scene depicted in the image, generating (120) a second depth map for the image, wherein a depth value associated with a pixel in the second depth map is based on depth values in the first depth map within a region spatially proximate to the pixel and at least one of color and luminance values of the image within the region and generating (130) a third depth map for the image using depth values from the first depth map and the second depth map, the generating scaling a depth difference, such that a difference between a depth value of the third and first depth map is scaled compared to the corresponding difference between a depth value of the second and first depth map. The invention further relates to a computer program product for use in executing the method according to the present invention.
|
