Finds a free port.

Given a path to a tyro CLI, write a completion script to a target directory. Args: script_path: Path to Python CLI to generate completion

Abstract method that returns the dataparser outputs for the given split. Args: split: Which dataset split to generate (train/test

Generates rays for the given camera indices and coords where self isn't jagged This is a fairly complex function, so let's break this down sl

Returns a list of batches from the dataset attribute.

Returns batch shapes of all tensors in a dictionary Args: dict_: The dictionary to get the batch shapes of. Returns:

compute the geometric initialization radius

compute input positions (for positional encoding / feature encoding) from raw ray sample positions.

compute input positions (for positional encoding / feature encoding) from raw ray sample positions. NOTE: assume the whole scene is r

visualizing ray-box intersection results

ignore ray samples in bg regions if the ray intersects the bottom plane.

Handle rays not intersecting the foreground AABB. Assign 0 weights for all fg queries and 1 for bg_transmittance to these rays. Retur

Parses the __init__() argument camera_type Camera Type Calculation: If CameraType, convert to int and then to tensor, then b

Initializes viewer scene with given train dataset

Returns collection of valid rays within a specified near/far bounding box along with a mask specifying which rays are valid Args:

Compute nears and fars for all rays.

Helper function to load pipeline and optimizer from prespecified checkpoint

only load normal for now

Load and precrocess coarse decomposition results ({fg, bg} {ptcd, feats})

Load camera poses

load and preprocess data for pointcloud regularization

Compute per ray_sample fg masks and bg masks

Parse images from camera dict, which is useful when there are too many frames. TODO: images not in the camera dict can be used during validat

Parse train / val / test split.

Determine indicies of images to display in viewer. Args: total_num: total number of training images. Returns:

helper to print out the stats in a readable format Args: latest_map: the most recent dictionary of stats that have been recorded

register all Tensor attributes as buffers to automatically move them to the target device

register all Tensor attributes as buffers to automatically move them to the target device

remove internal isolated geometries caused by hash encoding and insufficent regularization of internal regions.

Helper function to create a video of the spiral trajectory. Args: pipeline: Pipeline to evaluate with. cameras: Cameras to render

Helper function to create a video of the spiral trajectory. Args: pipeline: Pipeline to evaluate with. cameras: Cameras to render

Advanced string replacement. Given a text: - replace all elements in src by the corresponding element in tgt - remove all elements in rm

Chooses the correct output and sends it to the viewer Args: outputs: the dictionary of outputs to choose from, from the graph

Set randomness seed in torch and numpy

TODO: Implement CUDA & CPP versions.

Updates the dynamic number of rays per batch variable, based on the total number of samples in the last batch of rays.

helper to handle the printing of the header labels Args: latest_map: the most recent dictionary of stats that have been recorded

update outputs for loss computation

Try to add a `source /.../completions/setup.{shell}` line automatically to a user's zshrc or bashrc. Args: completions_dir: Path to locat