kornia.geometry.depth

kornia.geometry.depth.depth_from_disparity(disparity, baseline, focal)

Computes depth from disparity.

Parameters:
  • disparity (Tensor) – Disparity tensor of shape \((*, H, W)\).

  • baseline (float | Tensor) – float/tensor containing the distance between the two lenses.

  • focal (float | Tensor) – float/tensor containing the focal length.

Return type:

Tensor

Returns:

Depth map of the shape \((*, H, W)\).

Example

>>> disparity = torch.rand(4, 1, 4, 4)
>>> baseline = torch.rand(1)
>>> focal = torch.rand(1)
>>> depth_from_disparity(disparity, baseline, focal).shape
torch.Size([4, 1, 4, 4])
kornia.geometry.depth.depth_to_3d(depth, camera_matrix, normalize_points=False)

Compute a 3d point per pixel given its depth value and the camera intrinsics.

Note

This is an alternative implementation of depth_to_3d that does not require the creation of a meshgrid. In future, we will support only this implementation.

Parameters:
  • depth (Tensor) – image tensor containing a depth value per pixel with shape \((B, 1, H, W)\).

  • camera_matrix (Tensor) – tensor containing the camera intrinsics with shape \((B, 3, 3)\).

  • normalize_points (bool, optional) – whether to normalise the pointcloud. This must be set to True when the depth is represented as the Euclidean ray length from the camera position. Default: False

Return type:

Tensor

Returns:

tensor with a 3d point per pixel of the same resolution as the input \((B, 3, H, W)\).

Example

>>> depth = torch.rand(1, 1, 4, 4)
>>> K = torch.eye(3)[None]
>>> depth_to_3d(depth, K).shape
torch.Size([1, 3, 4, 4])
kornia.geometry.depth.depth_to_3d_v2(depth, camera_matrix, normalize_points=False, xyz_grid=None)

Compute a 3d point per pixel given its depth value and the camera intrinsics.

Note

This is an alternative implementation of kornia.geometry.depth.depth_to_3d() that does not require the creation of a meshgrid.

Parameters:
  • depth (Tensor) – image tensor containing a depth value per pixel with shape \((*, H, W)\).

  • camera_matrix (Tensor) – tensor containing the camera intrinsics with shape \((*, 3, 3)\).

  • normalize_points (bool, optional) – whether to normalise the pointcloud. This must be set to True when the depth is represented as the Euclidean ray length from the camera position. Default: False

Return type:

Tensor

Returns:

tensor with a 3d point per pixel of the same resolution as the input \((*, H, W, 3)\).

Example

>>> depth = torch.rand(4, 4)
>>> K = torch.eye(3)
>>> depth_to_3d_v2(depth, K).shape
torch.Size([4, 4, 3])
kornia.geometry.depth.unproject_meshgrid(height, width, camera_matrix, normalize_points=False, device=None, dtype=None)

Compute a 3d point per pixel given its depth value and the camera intrinsics.

Tip

This function should be used in conjunction with kornia.geometry.depth.depth_to_3d_v2() to cache the meshgrid computation when warping multiple frames with the same camera intrinsics.

Parameters:
  • camera_matrix (Tensor) – tensor containing the camera intrinsics with shape \((3, 3)\).

  • normalize_points (bool, optional) – whether to normalize the pointcloud. This must be set to True when the depth is represented as the Euclidean ray length from the camera position. Default: False

Return type:

Tensor

Returns:

tensor with a 3d point per pixel of the same resolution as the input \((*, H, W, 3)\).

kornia.geometry.depth.depth_to_normals(depth, camera_matrix, normalize_points=False)

Compute the normal surface per pixel.

Parameters:
  • depth (Tensor) – image tensor containing a depth value per pixel with shape \((B, 1, H, W)\).

  • camera_matrix (Tensor) – tensor containing the camera intrinsics with shape \((B, 3, 3)\).

  • normalize_points (bool, optional) – whether to normalize the pointcloud. This must be set to True when the depth is Default: False

  • position. (represented as the Euclidean ray length from the camera)

Return type:

Tensor

Returns:

tensor with a normal surface vector per pixel of the same resolution as the input \((B, 3, H, W)\).

Example

>>> depth = torch.rand(1, 1, 4, 4)
>>> K = torch.eye(3)[None]
>>> depth_to_normals(depth, K).shape
torch.Size([1, 3, 4, 4])
kornia.geometry.depth.depth_from_plane_equation(plane_normals, plane_offsets, points_uv, camera_matrix, eps=1e-8)

Compute depth values from plane equations and pixel coordinates.

Parameters:
  • plane_normals (Tensor) – Plane normal vectors of shape (B, 3).

  • plane_offsets (Tensor) – Plane offsets of shape (B, 1).

  • points_uv (Tensor) – Pixel coordinates of shape (B, N, 2).

  • camera_matrix (Tensor) – Camera intrinsic matrix of shape (B, 3, 3).

Returns:

Computed depth values at the given pixels, shape (B, N).

Return type:

Tensor

kornia.geometry.depth.warp_frame_depth(image_src, depth_dst, src_trans_dst, camera_matrix, normalize_points=False)

Warp a tensor from a source to destination frame by the depth in the destination.

Compute 3d points from the depth, transform them using given transformation, then project the point cloud to an image plane.

Parameters:
  • image_src (Tensor) – image tensor in the source frame with shape \((B,D,H,W)\).

  • depth_dst (Tensor) – depth tensor in the destination frame with shape \((B,1,H,W)\).

  • src_trans_dst (Tensor) – transformation matrix from destination to source with shape \((B,4,4)\).

  • camera_matrix (Tensor) – tensor containing the camera intrinsics with shape \((B,3,3)\).

  • normalize_points (bool, optional) – whether to normalize the pointcloud. This must be set to True when the depth is represented as the Euclidean ray length from the camera position. Default: False

Return type:

Tensor

Returns:

the warped tensor in the source frame with shape \((B,3,H,W)\).