Potential bug when creating image crops about equivariant-transporter-net HOT 4 CLOSED

Hi, the image was padded.

from equivariant-transporter-net.

Hi,
true, however it is padded by crop_size/2 in every direction (up, left, down, right) in the Attention and the Transport network.
e.g.

self.pad_size_1 = int(self.crop_size_1 / 2)
self.padding_1 = np.zeros((3, 2), dtype=int)
self.padding_1[:2, :] = self.pad_size_1

Which actually illustrates my point, because padding by crop_size/2 would make sense if the crop is centered around p, since then the maximum overlap over the input image boundaries would be crop_size/2. This would be figure B in the following drawing.

Figure A shows the way cropping is implemented as I understood it, which could lead to overlap over the padded area.
Figure B shows the cropping centered around the pixel p.

from equivariant-transporter-net.

Hi,

The coordinate of P changes after padding since the reference frame changed. For example, the coordinate of the upper left corner of the original image is (0,0) and after padding with 10 pixels on the four sides of the image, the coordinate of the upper left corner of the original image is (10, 10) instead of (0,0).

from equivariant-transporter-net.

Aah that makes sense.
Thanks for the explanation!

from equivariant-transporter-net.