| 摘要 |
When transforming a 2.5D video format to a plurality of images viewed from different virtual positions, it can occur that for certain output pixels, no input data is available. Therefore, these output pixels do not have any definite values assigned in their pixel locations. These unassigned pixel values cause artifacts called 'holes' in the transformed images. A method of hole filling or assigning pixel values in a region (110) comprising pixel locations of unassigned pixel values in an image (100) is provided. A direction (140) of an image feature (160) relative to a first pixel location (120) is estimated in a first neighbourhood (130) adjoining the region (110) of unassigned pixel values. A second set of pixel values is selected from pixel locations in the estimated direction (140) from the first pixel location (120). A third set of pixel values are computed from the second set of pixel values. At least apart of the region (110) comprising pixel locations of unassigned pixels is assigned with pixel values by using the third set of pixel values. The method is useful in reducing the visual distortion in the image compared to known methods.
|
