Closed YoussefFathi closed 4 years ago
Since spatial transformations will lead in a change to coordinates, we should sample optical flow on the view of transformed coordinates rather than the original one.
In this code, inverse_transform_coords()
transform coordinates:
and
transform_coords()
is its inverse operation.
I would appreciate it if you can clarify for me the following points related to specific parts of the "sp_transforms.py" file :
In _transformflow() , what is the purpose of the following block of code ?
` # inverse transform coords x0, y0 = self.inverse_transform_coords( width=width, height=height, thetas=theta1)
Why didn't you use only the following part of the code to transform the optical flow just like the _transform_image()_ function ?
What is the difference between the functionality of _inverse_transform_coords() and transform_coords()_ ?