Reprojection method, for when the absolute depth is known: 1) estimate the camera focal using a robust estimator 2) reproject points

Convert transformation matrix to quaternion and translation.

Runs multidimensional B-spline interpolation on the input points.

Normalization helper function.

Pad [..., 3, 4] pose matrices with a homogeneous bottom row [0,0,0,1].

Converts from (position, lookat, up) format to pose matrices.

extract confidence from prediction head output

Leverage TSDF to post-process estimated depths for each pixel, find zero level of TSDF along ray (or closest to 0)

Align the origin (0,0,1) with the target point (x,y,1) in projective space. Method: rotate z to put target on (x'+,0,1), then rotate on Y to get

calculate s, R, t so that: gt = R * s * est + t method can be: sim3, se3, posyaw, none; n_aligned: -1 means using all the frames

Return unit sphere coordinates from window coordinates.

Args: - depthmap (HxW array): - camera_intrinsics: a 3x3 matrix Returns: pointmap of absolute coordinates (HxWx3 arra

Evaluate spherical harmonics at unit directions using hardcoded SH polynomials. Works with torch/np/jnp. ... Can be 0 or more batch d

Creates a smooth spline path between input keyframe camera poses. Spline is calculated with poses in format (position, lookat-point, up-point).

Convert quaternion and translation to transformation matrix.

Get sorted image files from the given directory. Args: image_dir (str): Path to the directory containing images. Returns:

build a prediction head for the decoder