A command's raison d'etre: carry out the action it exists to perform, controlled by the options initialized in 'initialize_options()',

Transform points from world space (3 coordinates) to pixel space (2 coordinates). Args: points (torch.Tensor): Should have shape

Transform points from view space to world space. Args: points (torch.Tensor): Should have shape (n_cameras, N, 3). cameras (List[

Unflatten the voronoi features into a 3D tensor with shape (n_gaussians, n_voronoi_per_gaussians, *voronoi_features.shape[1:]). Args: vor

Learning rate scheduling per step

Evaluate the TSDF values at the given points using Depth Fusion. Args: points (torch.Tensor): Points at which to compute the TSDF. Has sh

Background tensor (bg_color) must be on GPU!

Returns torch.sqrt(torch.max(0, x)) but with a zero subgradient where x is 0.

unbatched marching tetrahedra. Refer to :func:`marching_tetrahedra`.

_summary_ Args: model (DepthAnythingV2): _description_ image (torch.Tensor): Has shape (H, W, 3) and RGB format. Values are betwe

Starting from initial SDF values, progressively linearize the SDF values to make them match a set of isosurface vertices after applying March

Compute associated Legendre polynomial coefficients. Returns the coefficient of the cos^k(theta)*sin^m(theta) term in the (l, m)th associated Leg

Calculate the average pose, which is then used to center all poses using @center_poses. Its computation is as follows: 1. Compute the cen

Calculates the least-squares best-fit transform that maps corresponding points A to B in m spatial dimensions Input: A: Nxm numpy array

Compute a loss encouraging pixels in 'depth' to have the same relative depth order as in 'prior_depth'. This loss does not require prior depth map

Extract mesh from scene representation and save mesh to file. Args: mesh_out_file: (str), output mesh filena

Estimate the bounding sphere given camera pose

Evaluate spherical harmonics bases at unit directions, without taking linear combination. At each point, the final result may the be

Adapted from Go-Surf: https://github.com/JingwenWang95/go-surf

Perform TSDF fusion given a fixed depth range, used in the paper. voxel_size: the voxel size of the volume sdf_trunc

_summary_ Args: view (_type_): _description_ normal (_type_): Returns: _type_: _description_

Calculate nearest point to all focal axes in poses.

Compute generalized binomial coefficients.

Generate integrated directional encoding (IDE) function. This function returns a function that computes the integrated directional encoding from

Copied from Plenoxels Continuous learning rate decay function. Adapted from JaxNeRF The returned rate is lr_init when step=0 and lr_fina