Raycast to check if point is in or on surface of mesh. Returns 1 if in, -1 else. Only to be used in robust mode

* Called during search to add an element matching the criteria. * @return true if the search should be continued, false if the results are * suf

Add points to the set, Inserts all points from [start, end] */

Adds gaussian noise to `raw`, which can used to regularize it. Args: key: jnp.ndarray(float32), [2,], random number generator. raw: jnp.nda

Find barycentric coords of p in triangle (a,b,c) in 3D (p does NOT have to be projected to plane beforehand) normal, area_abc to be computed using uti

* Builds the index */

Cast rays (cone- or cylinder-shaped) and featurize sections of it. Args: t_vals: float array, the "fencepost" distances along the ray. orig

Checks that value is larger than one. If so, return integer version of it, otherwise raises error :param value: float :raise: argparseArgumentTyp

Query for the closest points to a given point (entered as query_point[0:dim-1]).

Compute psnr value given mse (we assume the maximum pixel value is 1). Args: mse: float, mean square error of pixels. Returns: psnr: flo

Computes SSIM from two images. This function was modeled after tf.image.ssim, and should produce comparable output. Args: img0: array. An

Approximate a conical frustum as a Gaussian distribution (mean+cov). Assumes the ray is originating from the origin, and base_radius is the radiu

Construct a Neural Radiance Field. Args: key: jnp.ndarray. Random number generator. example_batch: dict, an example of a batch of data.

Convolution by 3D Gaussian kernel. Args: - grid: np.ndarray, refractive index, [N_x * N_y * N_z, 1] - ndim: list, the resolution of voxel gr

Approximate a cylinder as a Gaussian distribution (mean+cov). Assumes the ray is originating from the origin, and radius is the radius. Does not

Define flags for both training and evaluation modes.

https://github.com/NVlabs/tiny-cuda-nn/blob/master/include/tiny-cuda-nn/encodings/spherical_harmonics.h Args: - data_in: jnp.ndarray, viewd

3D point to line shortest distance SQUARED

3D point to triangle shortest distance SQUARED normal, area_abc to be computed using util::normal, where normal is normalized vector, area is magnitud

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

A helper function that wraps around a 'model zoo'.

Creates multiple empty trees to handle dynamic support */

Make sure the auxiliary list \a vind has the same size than the current * dataset, and re-generate if size has changed. */

Encode `x` with sinusoids scaled by 2^[min_deg:max_deg-1]. Args: x_coord: a tuple containing: x, jnp.ndarray, variables to be encoded. Should

Returns the distance between the vector "p1[0:size-1]" and the data point with index "idx_p2" stored in the class:

Returns the dim'th component of the idx'th point in the class:

* Find the "num_closest" nearest neighbors to the \a query_point[0:dim-1]. * Their indices are stored inside the result object. \sa radiusSearch,

* Find the "num_closest" nearest neighbors to the \a query_point[0:dim-1]. * Their indices are stored inside the result object. \sa radiusSearch,

Continuous learning rate decay function. The returned rate is lr_init when step=0 and lr_final when step=max_steps, and is log-linearly interpola

Loads a previous index from a binary file. * IMPORTANT NOTE: The set of data points is NOT stored in the file, so the * index object must be c

Loads a previous index from a binary file. * IMPORTANT NOTE: The set of data points is NOT stored in the file, so the * index object must be c

Args: - from_here: jnp.ndarray, [square*square, 3] - to_there: jnp.ndarray, [batch, sample, 3] - dataset: string, up vector [0, 0, 1] f

jnp.matmul defaults to bfloat16, but this helper function doesn't.