Plot a set of images horizontally. Args: imgs: a list of NumPy or PyTorch images, RGB (H, W, 3) or mono (H, W). titles: a list of

Normalize the image tensor and reorder the dimensions.

Convert N-dimensional points to homogeneous coordinates. Args: points: torch.Tensor or numpy.ndarray with size (..., N). Returns:

Plot line matches for existing images with multiple colors. Args: lines: list of ndarrays of size (N, 2, 2). correct_matches: bool

Plot keypoints for existing images. Args: kpts: list of ndarrays of size (N, 2). colors: string, or list of list of tuples (one fo

Plot lines and endpoints for existing images. Args: lines: list of ndarrays of size (N, 2, 2). colors: string, or list of list of

Plot matches for a pair of existing images. Args: kpts0, kpts1: corresponding keypoints of size (N, 2). color: color of each match

Evaluate the thin-plate-spline (TPS) surface at xy locations arranged in a grid. The TPS surface is a minimum bend interpolation surface defined b

To be implemented by the child class.

To be implemented by the child class.

r"""Approximates the Manhattan distance transform of images using cascaded convolution operations. The value at each pixel in the output represen

Remove the homogeneous dimension of N-dimensional points. Args: points: torch.Tensor or numpy.ndarray with size (..., N+1). Returns:

Get the class object which inherits from BaseClass and is defined in the module named mod_name, child of base_path.

Given a set of lines, their score and dense descriptors, merge close-by endpoints and compute a wireframe defined by its junctions an

Shrink an array of segments to fit inside the image. :param segs: The tensor of segments with shape (N, 2, 2) :param img_shape: The image

Perform non maximum suppression on the heatmap using max-pooling. This method does not suppress contiguous points that have the same score. Ar

Create a skew-symmetric matrix from a (batched) vector of size (..., 3).

:param lines: A tensor of shape (B, N, 2, 2) where B is the batch size, N the number of lines. :param H: The homography used to convert the l

Warp a list of points with the INVERSE of the given homography. The inverse is used to be coherent with tf.contrib.image.transform Argume

Convert batched poses (..., 4, 4) to batched essential matrices.

Perform some logic and call the _init method of the child model.