Abstract:
A depth map is generated from at least a first and a second image. Generally, a plurality of reference pixels are selected in the first image and associated with respective pixels in the second image. Next, the disparity between each reference pixel and the respective pixel in said second image is determined, and for each reference pixel a depth value as a function of the respective disparity. In particular, each reference pixel is associated with a respective pixel in the second image via a matching and a filtering operation. The matching operation selects for each reference pixel a plurality of candidate pixels in the second image and associates with each candidate pixel a respective cost function value and a respective disparity value.