How to make a laplacian pyramid using OpenCV python

Question

I'm trying to get a layer of the Laplacian pyramid using the opencv functions: pyrUp and pyrDown.

I'm trying to create a Laplacian pyramid using OpenCV. According to the openCV documentation, there is a way to do this using the following expression:

Li = Gi - pyrDown(Gi+1)

where Gi is the i-th layer of the Gaussian pyramid.

This is is what I've been able to do till now

def get_laplacian_pyramid_layer(img, n):
    gi = img
    for i in range(n):
        gi_prev = gi
        gi = cv2.pyrDown(gi_prev)
    pyrup = cv2.pyrUp(gi)
    return cv2.addWeighted(gi_prev, 1.5, pyrup, -0.5, 0)

The problem is that I get different sizes of the images that are used in the subtractions. And I have no clue why this is happening

Answer 1

down voteacceptTheeThe problem is that you're iterating pyrDown everytime 

down = cv2.pyrDown(img)

change that line to

down = cv2.pyrDown(currImg)

so you actually compute the next pyramid layer.

The reason for the error is your down image. Its shape is width/2 x height/2 compared to the input image

down = cv2.pyrDown(img)

yet you try to store its pyrUp result (width * height) in a much smaller up image with its shape beeing smaller (width/2 x height/2) due to

up = cv2.pyrUp(down, dstsize=currImg.shape)
...
currImg = down 

down voteaccepted

Answer 2

However, this code also gives me an error when when executing the pyrUp >function. The message of the error is:

OpenCV Error: Assertion failed (std::abs(dsize.width - ssize.width*2) == >dsize.width % 2 && std::abs(dsize.height - ssize.height*2) == dsize.height % >2) in pyrUp_,

Many years late to the party here, but here we go. When passing the upscaled image size using 'dstsize:

up = cv2.pyrUp(down, dstsize=currImg.shape)

the .shape method returns height x width. However, the pyrup function requires these dimensions as width x height. Therefore try the following code:

up = cv2.pyrUp(down, dstsize=(currImg.shape[1],currImg.shape[0])