Entrypoint for use with pyproject scripts.

Entrypoint for use with pyproject scripts.

Entrypoint for use with pyproject scripts.

The main entrypoint.

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

Run one iteration with different batch/image/all image evaluations depending on step size. Args: step: Current training step.

Helper function to load checkpointed pipeline Args: config (DictConfig): Configuration of pipeline to load pipeline (Pipeline): P

:param data_dir: the root dir of NYUDv2 :param save_dir: the root dir to save the result :param model_path: the path of the model(.pth fi

evenly sample n_samples from elems and keep the start & last elements.

Compute the exponential map of the direct product group `SO(3) x R^3`. This can be used for learning pose deltas on SE(3), and is generally faste

Exports the mesh to a file. We use pymeshlab to export the mesh as a PLY file. Args: mesh: The mesh to export.

Farthest point sampling. Args: dist: NxN distance matrix. N: Number of points to sample. dist_thresh: Distance threshold.

query foreground fields and rendering

! For n != 0, returns k, such that pow10 := 10^(k-1) <= n < 10^k. For n == 0, returns 1 and sets pow10 := 1. */

flow_utils.flowMaxNorm(flow): return the maximum of the l2-norm of the given flow ---- PARAMETERS ---- flow: the flow --

flow_utils.flowToColor(flow): return a color code flow field, normalized based on the maximum l2-norm of the flow flow_utils.flowToColor(flow

Sets the codec preferences on a connection between sender and reciever Args: pc: peer connection point sender: sender that will s

Process network output for renderer Args: in_tensor: Network input Returns: Render head output

Forward the fg field and mask out weights of points outside the fg aabb.

Returns an instance of TSDF from an axis-aligned bounding box and volume dimensions. Args: aabb: The axis-aligned bounding box wi

Generate random crops of size=resolution, for an input image upscaled to (imsize + randint(0 , aug_crop))

Generate tuples of overlapping views for a given scene. generate_depth: generate depth images and camera parameters.

Generate images from a metadata file for reproducibility purposes.

Generate Ray Samples

extract 3D_model (glb file) from a reconstructed scene

compute alpha from sdf as in NeuS

return current beta value

! For a normalized diyfp w = f * 2^e, this function returns a (normalized) cached power-of-ten c = f_c * 2^e_c, such that the exponent of the product

Get camera for the given image index Args: image_idx: Camera image index

Returns list of n elements, constaining a sublist. Args: lst: List to be chunked up num_chunks: number of chunks to split list in

Returns the version of COLMAP. This code assumes that colmap returns a version string of the form "COLMAP 3.8 ..." which may not be true for a

compute colors

Calculating the bound d* (Theorem 1) from VolSDF

This function gets your evaluation loss dict. It needs to get the data from the DataManager and feed it to the model's forward function

This function gets your evaluation loss dict. It needs to get the data from the DataManager and feed it to the model's forward function

Reads or computes the focal length from transforms dict. Args: meta: metadata from transforms.json file. Returns:

Get a plotly mesh for a single frustum. Args: frustum: Single frustum opacity: Opacity of the mesh. Defaults to 0.3. colo

Get a plotly ellipsoid for a Gaussian. Args: mean: mean of the Gaussian. cov: covariance of the Gaussian. n_std: Standard

get homography Args: intersection_points (torch.Tensor): _description_ normal (torch.Tensor): _description_ cameras (Came

Returns a 3 channel image. Args: image_idx: The image index in the dataset.

Returns interpolated path between two camera poses with specified number of steps. Args: KA: camera matrix 1 KB: camera matr

Return interpolation of poses with specified number of steps. Args: poseA: first pose poseB: second pose steps: number of

Return interpolated poses for many camera poses. Args: poses: list of camera poses Ks: list of camera intrinsics steps_pe

compute intersection points Args: ray_samples (RaySamples): _description_ sdf (torch.Tensor): _description_ normal (torch

Returns the camera intrinsics matrix and the camera to world homogeneous matrix. Args: camera_object: a Camera object. image_size

Returns a list of Scatter3D objects for creating lines with plotly. # TODO(ethan): make this function more efficient instead of having a list of o

The rank of the current process within the local (per-machine) process group.

Extracts a mesh using marching cubes.