# tf.contrib.image.sparse_image_warp

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/contrib/image/python/ops/sparse_image_warp.py#L104-L202) |

Image warping using correspondences between sparse control points.

    tf.contrib.image.sparse_image_warp(
        image, source_control_point_locations, dest_control_point_locations,
        interpolation_order=2, regularization_weight=0.0, num_boundary_points=0,
        name='sparse_image_warp'
    )

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`](https://www.tensorflow.org/versions/r1.15/api_docs/python/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`](https://www.tensorflow.org/versions/r1.15/api_docs/python/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`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/image/interpolate_spline) for further documentation of the
interpolation_order and regularization_weight arguments.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `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). <br /> Note that image and offsets can be of type tf.half, tf.float32, or tf.float64, and do not necessarily have to be the same type. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| `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. |

<br />