Image pyramids (Gaussian and Laplacian) – blending images

We can construct the Gaussian pyramid of an image by starting with the original image and creating smaller images iteratively, first by smoothing (with a Gaussian filter to avoid anti-aliasing), and then by subsampling (collectively called reducing) from the previous level's image at each iteration until a minimum resolution is reached. The image pyramid created in this way is called a Gaussian pyramid. These are good for searching over scale (for instance, template-matching), precomputation, and image processing tasks by editing frequency bands separately (for instance, image blending). Similarly, a Laplacian pyramid for the image can be constructed by starting from the smallest sized image in the Gaussian pyramid and then by expanding (up-sampling plus smoothing) the image from that level and subtracting it from the image from the next level of the Gaussian pyramid, and repeating this process iteratively until the original image...