kornia.geometry.keypoints

Module with useful functionalities for 2D and 3D keypoints manipulation.

class kornia.geometry.keypoints.Keypoints(keypoints, raise_if_not_floating_point=True)

2D Keypoints containing Nx2 or BxNx2 points.

Parameters:

• keypoints (Union[Tensor, List[Tensor]]) – Raw tensor or a list of Tensors with the Nx2 coordinates

• raise_if_not_floating_point (bool, optional) – will raise if the Tensor isn’t float Default: True

clone()

Return type:

Keypoints

property data: Tensor

property device: device

Returns keypoints device.

property dtype: dtype

Returns keypoints dtype.

classmethod from_tensor(keypoints)

Return type:

Keypoints

index_put(indices, values, inplace=False)

Return type:

Keypoints

pad(padding_size)

Pad a bounding keypoints.

Parameters:

padding_size (Tensor) – (B, 4)

Return type:

Keypoints

property shape: Tuple[int, ...] | Size

to_tensor(as_padded_sequence=False)

Cast Keypoints to a tensor. mode controls which 2D keypoints format should be use to represent keypoints in the tensor.

Parameters:

as_padded_sequence (bool, optional) – whether to keep the pads for a list of keypoints. This parameter is only valid if the keypoints are from a keypoint list. Default: False

Return type:

Union[Tensor, List[Tensor]]

Returns:

Keypoints tensor \((B, N, 2)\)

transform_keypoints(M, inplace=False)

Apply a transformation matrix to the 2D keypoints.

Parameters:

• M (Tensor) – The transformation matrix to be applied, shape of \((3, 3)\) or \((B, 3, 3)\).

• inplace (bool, optional) – do transform in-place and return self. Default: False

Return type:

Keypoints

Returns:

The transformed keypoints.

transform_keypoints_(M)

Inplace version of Keypoints.transform_keypoints()

Return type:

Keypoints

type(dtype)

Return type:

Keypoints

unpad(padding_size)

Pad a bounding keypoints.

Parameters:

padding_size (Tensor) – (B, 4)

Return type:

Keypoints

class kornia.geometry.keypoints.Keypoints3D(keypoints, raise_if_not_floating_point=True)

3D Keypoints containing Nx3 or BxNx3 points.

Parameters:

• keypoints (Union[Tensor, List[Tensor]]) – Raw tensor or a list of Tensors with the Nx3 coordinates

• raise_if_not_floating_point (bool, optional) – will raise if the Tensor isn’t float Default: True

clone()

Return type:

Keypoints3D

property data: Tensor

classmethod from_tensor(keypoints)

Return type:

Keypoints3D

pad(padding_size)

Pad a bounding keypoints.

Parameters:

padding_size (Tensor) – (B, 6)

Return type:

Keypoints3D

property shape: Size

to_tensor(as_padded_sequence=False)

Cast Keypoints to a tensor. mode controls which 2D keypoints format should be use to represent keypoints in the tensor.

Parameters:

as_padded_sequence (bool, optional) – whether to keep the pads for a list of keypoints. This parameter is only valid if the keypoints are from a keypoint list. Default: False

Return type:

Union[Tensor, List[Tensor]]

Returns:

Keypoints tensor \((B, N, 3)\)

transform_keypoints(M, inplace=False)

Apply a transformation matrix to the 2D keypoints.

Parameters:

• M (Tensor) – The transformation matrix to be applied, shape of \((3, 3)\) or \((B, 3, 3)\).

• inplace (bool, optional) – do transform in-place and return self. Default: False

Return type:

Keypoints3D

Returns:

The transformed keypoints.

transform_keypoints_(M)

Inplace version of Keypoints.transform_keypoints()

Return type:

Keypoints3D

unpad(padding_size)

Pad a bounding keypoints.

Parameters:

padding_size (Tensor) – (B, 6)

Return type:

Keypoints3D