vision3d.transforms.functional#

Functional form of the 3D transforms in vision3d.transforms.

Functions

`center_crop_camera_intrinsics`(inpt, output_size)	Update `CameraIntrinsics` for a center crop of the corresponding image.
`crop_camera_intrinsics`(inpt, top, left, ...)	Update `CameraIntrinsics` for a crop of the corresponding image.
`flip_3d`(inpt, *, axis)	Flip a tensor along a 3D spatial axis.
`flip_3d_bounding_boxes`(boxes, *, format, axis)	Flip 3D bounding boxes along `axis`.
`flip_3d_point_cloud`(points, *, axis)	Flip point cloud coordinates along `axis`.
`jitter_points`(inpt, *, noise)	Dispatcher entry point for point jittering.
`jitter_points_point_cloud`(points, *, noise)	Add noise to point xyz coordinates.
`pad_camera_intrinsics`(inpt, padding, **kwargs)	Update `CameraIntrinsics` for a pad of the corresponding image.
`register_kernel`(functional, tv_tensor_cls, *)	Register a kernel for a functional and TVTensor type.
`resize_camera_intrinsics`(inpt, size[, max_size])	Update `CameraIntrinsics` for a resize of the corresponding image.
`resized_crop_camera_intrinsics`(inpt, top, ...)	Update `CameraIntrinsics` for a crop followed by a resize.
`rotate_3d`(inpt, *, rotation_matrix)	Rotate a tensor by a 3x3 rotation matrix.
`rotate_3d_bounding_boxes`(boxes, *, format, ...)	Rotate 3D bounding boxes by `rotation_matrix`.
`rotate_3d_camera_extrinsics`(extrinsics, *, ...)	Update camera extrinsics after rotating the lidar frame.
`rotate_3d_point_cloud`(points, *, rotation_matrix)	Rotate point cloud coordinates by `rotation_matrix`.
`sample_points`(inpt, *, indices)	Dispatcher entry point for point sampling.
`sample_points_point_cloud`(points, *, indices)	Select points by index.
`scale_3d`(inpt, *, factor)	Scale a tensor by a uniform factor.
`scale_3d_bounding_boxes`(boxes, *, format, factor)	Scale 3D bounding boxes by `factor`.
`scale_3d_camera_extrinsics`(extrinsics, *, factor)	Update camera extrinsics after scaling the lidar frame.
`scale_3d_point_cloud`(points, *, factor)	Scale point cloud coordinates by `factor`.
`shuffle_points`(inpt, *, perm)	Dispatcher entry point for point shuffling.
`shuffle_points_point_cloud`(points, *, perm)	Permute point order.
`translate_3d`(inpt, *, offset)	Translate a tensor by a 3D offset.
`translate_3d_bounding_boxes`(boxes, *, ...)	Translate 3D bounding boxes by `offset`.
`translate_3d_camera_extrinsics`(extrinsics, ...)	Update camera extrinsics after translating the lidar frame.
`translate_3d_point_cloud`(points, *, offset)	Translate point cloud coordinates by `offset`.

vision3d.transforms.functional.center_crop_camera_intrinsics(inpt, output_size)[source]#

Update CameraIntrinsics for a center crop of the corresponding image.

Parameters:

inpt (CameraIntrinsics) – The intrinsics to update.
output_size (list[int]) – Target (h, w) after the center crop.

Returns:

Updated intrinsics with image_size set to output_size.

Return type:

CameraIntrinsics

vision3d.transforms.functional.crop_camera_intrinsics(inpt, top, left, height, width)[source]#

Update CameraIntrinsics for a crop of the corresponding image.

Shifts the principal point so projection through the updated intrinsics matches projection through the original intrinsics on the cropped image.

Parameters:

inpt (CameraIntrinsics) – The intrinsics to update.
top (int) – Top edge of the crop in pixels.
left (int) – Left edge of the crop in pixels.
height (int) – Crop height in pixels.
width (int) – Crop width in pixels.

Returns:

Updated intrinsics with image_size set to (height, width).

Return type:

CameraIntrinsics

vision3d.transforms.functional.flip_3d(inpt, *, axis)[source]#

Flip a tensor along a 3D spatial axis.

This is the dispatcher entry point. Type-specific kernels are registered below.

Parameters:

inpt (Tensor) – Input tensor.
axis (str) – One of "x", "y", "z".

Returns:

Flipped tensor.

Return type:

Tensor

vision3d.transforms.functional.flip_3d_bounding_boxes(boxes, *, format, axis)[source]#

Flip 3D bounding boxes along axis.

Parameters:

boxes (Tensor) – Bounding box tensor [..., K].
format (BoundingBox3DFormat) – Format of the boxes.
axis (str) – One of "x", "y", "z".

Returns:

Flipped bounding boxes with the same shape.

Return type:

Tensor

vision3d.transforms.functional.flip_3d_point_cloud(points, *, axis)[source]#

Flip point cloud coordinates along axis.

Parameters:

points (Tensor) – Point cloud tensor [..., 3+C].
axis (str) – One of "x", "y", "z".

Returns:

Flipped point cloud with the same shape.

Return type:

Tensor

vision3d.transforms.functional.jitter_points(inpt, *, noise)[source]#

Dispatcher entry point for point jittering.

Returns:

Input unchanged (passthrough for non-point types).

Parameters:

inpt (Tensor)
noise (Tensor)

Return type:

Tensor

vision3d.transforms.functional.jitter_points_point_cloud(points, *, noise)[source]#

Add noise to point xyz coordinates.

Parameters:

points (Tensor) – Point cloud [N, 3+C].
noise (Tensor) – Additive noise [N, 3].

Returns:

Jittered point cloud with the same shape. Non-xyz features are unchanged.

Return type:

Tensor

vision3d.transforms.functional.pad_camera_intrinsics(inpt, padding, **kwargs)[source]#

Update CameraIntrinsics for a pad of the corresponding image.

Shifts the principal point by the top-left pad and grows image_size to include the padded borders.

Parameters:

inpt (CameraIntrinsics) – The intrinsics to update.
padding (int | list[int]) – Padding spec as accepted by torchvision.transforms.v2.functional.pad().
kwargs (Any) – Unused; accepted for signature compatibility with torchvision.transforms.v2.functional.pad().

Returns:

Updated intrinsics with the padded image_size.

Return type:

CameraIntrinsics

vision3d.transforms.functional.register_kernel(functional, tv_tensor_cls, *, tv_tensor_wrapper=True)[source]#

Parameters:

functional (Callable[[...], Any]) – The functional to register a kernel for.
tv_tensor_cls (type[TVTensor]) – The TVTensor subclass this kernel handles.
tv_tensor_wrapper (bool) – If True (default), the kernel receives an unwrapped pure tensor and the output is automatically re-wrapped. If False, the kernel receives the full TVTensor and must handle wrap itself.

Returns:

Decorator that registers the kernel.

Return type:

Callable[[Callable[[…], Any]], Callable[[…], Any]]

vision3d.transforms.functional.resize_camera_intrinsics(inpt, size, max_size=None, **kwargs)[source]#

Update CameraIntrinsics for a resize of the corresponding image.

Scales the focal lengths, skew, and principal point so projection through the updated intrinsics matches projection through the original intrinsics on the resized image.

Parameters:

inpt (CameraIntrinsics) – The intrinsics to update.
size (list[int] | None) – Target (h, w) after resize.
max_size (int | None) – Optional cap on the longer edge.
kwargs (Any) – Unused; accepted for signature compatibility with torchvision.transforms.v2.functional.resize().

Returns:

Updated intrinsics with the new image_size.

Return type:

CameraIntrinsics

vision3d.transforms.functional.resized_crop_camera_intrinsics(inpt, top, left, height, width, size, **kwargs)[source]#

Update CameraIntrinsics for a crop followed by a resize.

Parameters:

inpt (CameraIntrinsics) – The intrinsics to update.
top (int) – Top edge of the crop in pixels.
left (int) – Left edge of the crop in pixels.
height (int) – Crop height in pixels.
width (int) – Crop width in pixels.
size (list[int]) – Target (h, w) after the resize.
kwargs (Any) – Unused; accepted for signature compatibility with torchvision.transforms.v2.functional.resized_crop().

Returns:

Updated intrinsics with image_size set to size.

Return type:

CameraIntrinsics

vision3d.transforms.functional.rotate_3d(inpt, *, rotation_matrix)[source]#

Rotate a tensor by a 3x3 rotation matrix.

Dispatcher entry point. Type-specific kernels are registered below.

Parameters:

inpt (Tensor) – Input tensor.
rotation_matrix (Tensor) – [3, 3] rotation matrix.

Returns:

Rotated tensor.

Return type:

Tensor

vision3d.transforms.functional.rotate_3d_bounding_boxes(boxes, *, format, rotation_matrix)[source]#

Rotate 3D bounding boxes by rotation_matrix.

Only rotated formats are supported:

XYZLWHY: only Z-axis rotations (pure yaw).
XYZLWHYPR: arbitrary rotations.

Axis-aligned formats (XYZXYZ, XYZLWH) cannot represent rotation and will raise NotImplementedError.

Parameters:

boxes (Tensor) – Bounding box tensor [..., K].
format (BoundingBox3DFormat) – Format of the boxes.
rotation_matrix (Tensor) – [3, 3] rotation matrix.

Returns:

Rotated bounding boxes with the same shape.

Raises:

NotImplementedError – If format is axis-aligned.
ValueError – If format is XYZLWHY and rotation is not pure yaw.

Return type:

Tensor

vision3d.transforms.functional.rotate_3d_camera_extrinsics(extrinsics, *, rotation_matrix)[source]#

Update camera extrinsics after rotating the lidar frame.

The lidar-to-camera extrinsic E satisfies p_cam = E @ p_lidar. After rotating the lidar frame by R, points become p' = R @ p, so E' = E @ R_inv to keep p_cam = E' @ p'.

Parameters:

extrinsics (Tensor) – Extrinsic matrices [..., 4, 4].
rotation_matrix (Tensor) – [3, 3] rotation matrix.

Returns:

Updated extrinsics with the same shape.

Return type:

Tensor

vision3d.transforms.functional.rotate_3d_point_cloud(points, *, rotation_matrix)[source]#

Rotate point cloud coordinates by rotation_matrix.

Parameters:

points (Tensor) – Point cloud tensor [..., 3+C].
rotation_matrix (Tensor) – [3, 3] rotation matrix.

Returns:

Rotated point cloud with the same shape.

Return type:

Tensor

vision3d.transforms.functional.sample_points(inpt, *, indices)[source]#

Dispatcher entry point for point sampling.

Returns:

Input unchanged (passthrough for non-point types).

Parameters:

inpt (Tensor)
indices (Tensor)

Return type:

Tensor

vision3d.transforms.functional.sample_points_point_cloud(points, *, indices)[source]#

Select points by index.

Parameters:

points (Tensor) – Point cloud [N, 3+C].
indices (Tensor) – Selection indices [M]. May contain repeats for oversampling.

Returns:

Selected point cloud [M, 3+C].

Return type:

Tensor

vision3d.transforms.functional.scale_3d(inpt, *, factor)[source]#

Scale a tensor by a uniform factor.

Dispatcher entry point. Type-specific kernels are registered below.

Parameters:

inpt (Tensor) – Input tensor.
factor (float) – Scale factor.

Returns:

Scaled tensor.

Return type:

Tensor

vision3d.transforms.functional.scale_3d_bounding_boxes(boxes, *, format, factor)[source]#

Scale 3D bounding boxes by factor.

Scales both position and dimensions. Rotation angles are unchanged.

Parameters:

boxes (Tensor) – Bounding box tensor [..., K].
format (BoundingBox3DFormat) – Format of the boxes.
factor (float) – Scale factor.

Returns:

Scaled bounding boxes with the same shape.

Return type:

Tensor

vision3d.transforms.functional.scale_3d_camera_extrinsics(extrinsics, *, factor)[source]#

Update camera extrinsics after scaling the lidar frame.

Parameters:

extrinsics (Tensor) – Extrinsic matrices [..., 4, 4].
factor (float) – Scale factor applied to the lidar frame.

Returns:

Updated extrinsics with the same shape.

Return type:

Tensor

vision3d.transforms.functional.scale_3d_point_cloud(points, *, factor)[source]#

Scale point cloud coordinates by factor.

Parameters:

points (Tensor) – Point cloud tensor [..., 3+C].
factor (float) – Scale factor.

Returns:

Scaled point cloud with the same shape.

Return type:

Tensor

vision3d.transforms.functional.shuffle_points(inpt, *, perm)[source]#

Dispatcher entry point for point shuffling.

Returns:

Input unchanged (passthrough for non-point types).

Parameters:

inpt (Tensor)
perm (Tensor)

Return type:

Tensor

vision3d.transforms.functional.shuffle_points_point_cloud(points, *, perm)[source]#

Permute point order.

Parameters:

points (Tensor) – Point cloud [N, 3+C].
perm (Tensor) – Permutation indices [N].

Returns:

Permuted point cloud with the same shape.

Return type:

Tensor

vision3d.transforms.functional.translate_3d(inpt, *, offset)[source]#

Translate a tensor by a 3D offset.

Dispatcher entry point. Type-specific kernels are registered below.

Parameters:

inpt (Tensor) – Input tensor.
offset (Tensor) – Translation [3] as (tx, ty, tz).

Returns:

Translated tensor.

Return type:

Tensor

vision3d.transforms.functional.translate_3d_bounding_boxes(boxes, *, format, offset)[source]#

Translate 3D bounding boxes by offset.

Parameters:

boxes (Tensor) – Bounding box tensor [..., K].
format (BoundingBox3DFormat) – Format of the boxes.
offset (Tensor) – Translation [3] as (tx, ty, tz).

Returns:

Translated bounding boxes with the same shape.

Return type:

Tensor

vision3d.transforms.functional.translate_3d_camera_extrinsics(extrinsics, *, offset)[source]#

Update camera extrinsics after translating the lidar frame.

The lidar-to-camera extrinsic translation changes because the lidar origin moved by offset in the lidar frame.

Parameters:

extrinsics (Tensor) – Extrinsic matrices [..., 4, 4].
offset (Tensor) – Translation [3] as (tx, ty, tz) in lidar frame.

Returns:

Updated extrinsics with the same shape.

Return type:

Tensor

vision3d.transforms.functional.translate_3d_point_cloud(points, *, offset)[source]#

Translate point cloud coordinates by offset.

Parameters:

points (Tensor) – Point cloud tensor [..., 3+C].
offset (Tensor) – Translation [3] as (tx, ty, tz).

Returns:

Translated point cloud with the same shape.

Return type:

Tensor