[Feat] OpenCV local feature orientation is oppositte

Now to extract the same patches as OpenCV one needs to convert by multiplication by -1:

from kornia.feature import laf_from_center_scale_ori as get_laf
def laf_from_opencv_kpts(kpts, mrSize=6.0, device=torch.device('cpu')):
    N = len(kpts)
    xy = torch.tensor([(x.pt[0], x.pt[1]) for x in kpts ], device=device, dtype=torch.float).view(1, N, 2)
    scales = torch.tensor([(mrSize * x.size) for x in kpts ], device=device, dtype=torch.float).view(1, N, 1, 1)
    angles = torch.tensor([(x.angle) for x in kpts ], device=device, dtype=torch.float).view(1, N, 1)
    laf = get_laf(xy, scales, -angles)
    return laf

ToDo: make the same direction, as in OpenCV.

[ducha-aiki]

@edgarriba I will do PR soon

[edgarriba]

@ducha-aiki what should we do here ?