img_sparse_image_warp: Sparse image warp
In tfaddons: Interface to 'TensorFlow SIG Addons'

Description Usage Arguments Details Value

Image warping using correspondences between sparse control points.

img_sparse_image_warp(
  image,
  source_control_point_locations,
  dest_control_point_locations,
  interpolation_order = 2,
  regularization_weight = 0,
  num_boundary_points = 0,
  name = "sparse_image_warp"
)

`image`	'[batch, height, width, channels]' float 'Tensor'
`source_control_point_locations`	'[batch, num_control_points, 2]' float 'Tensor'
`dest_control_point_locations`	'[batch, num_control_points, 2]' float 'Tensor'
`interpolation_order`	polynomial order used by the spline interpolation
`regularization_weight`	weight on smoothness regularizer in interpolation
`num_boundary_points`	How many zero-flow boundary points to include at each image edge. Usage: num_boundary_points=0: don't add zero-flow points num_boundary_points=1: 4 corners of the image num_boundary_points=2: 4 corners and one in the middle of each edge (8 points total) num_boundary_points=n: 4 corners and n-1 along each edge
`name`	A name for the operation (optional).

Apply a non-linear warp to the image, where the warp is specified by the source and destination locations of a (potentially small) number of control points. First, we use a polyharmonic spline ('tf$contrib$image$interpolate_spline') to interpolate the displacements between the corresponding control points to a dense flow field. Then, we warp the image using this dense flow field ('tf$contrib$image$dense_image_warp'). Let t index our control points. For regularization_weight=0, we have: warped_image[b, dest_control_point_locations[b, t, 0], dest_control_point_locations[b, t, 1], :] = image[b, source_control_point_locations[b, t, 0], source_control_point_locations[b, t, 1], :]. For regularization_weight > 0, this condition is met approximately, since regularized interpolation trades off smoothness of the interpolant vs. reconstruction of the interpolant at the control points. See 'tf$contrib$image$interpolate_spline' for further documentation of the interpolation_order and regularization_weight arguments.

warped_image: '[batch, height, width, channels]' float 'Tensor' with same type as input image. flow_field: '[batch, height, width, 2]' float 'Tensor' containing the dense flow field produced by the interpolation.

tfaddons documentation built on July 2, 2020, 2:12 a.m.