+Even for small images, the pyramid method achived over an 100x speedup, while for large images, the compute time is faster than using naive search to align 1 image. More concretely, because the image is downscaled by 2x at each layer of the pyramid, the total image area is less than 1 + (1/2)<sup>2</sup> + (1/4)<sup>2</sup> + (1/8)<sup>2</sup> + ... = 1 + 1/4 + 1/16 + 1/64 + ... < 4/3 of the original. Since the search at the lowest scale is limited to W ≤ 72, the total time complexity is only <i>4(3W)W / 3</i> + smaller terms = <i>O(W<sup>2</sup>)</i>, at least a full width factor faster than the naive method.
0 commit comments