Basic optimizer config with Adam

Path class Args: entries: component parts of the path

Full config contents

Configuration for training regimen

Configuration for pipeline instantiation

Configuration for viewer instantiation

Configuration for data manager instantiation; DataManager is in charge of keeping the train/eval dataparsers; After instantiation, data manager ho

Configuration of optimization for camera poses.

Basic scheduler config with self-defined exponential decay schedule

Dataparser outputs for the image dataset and the ray generator. Note: currently only supports cameras with the same principal points and types. T

Basic scheduler config with self-defined exponential decay schedule

Nerfacto Model Config

Scene dataset parser config

Data to represent the scene box.

AutoRecon dataset parser config

Callback class used during training. The function 'func' with 'args' and 'kwargs' will be called every 'update_every_num_iters' training iteration

Sample uniformly along a ray Args: num_samples: Number of samples per ray train_stratified: Use stratified sampling during traini

Multilayer perceptron Args: in_dim: Input layer dimension num_layers: Number of network layers layer_width: Width of each

Dataparser outputs for the which will be used by the DataManager for creating RayBundle and RayGT objects.

Multi-scale sinusoidal encodings. Support ``integrated positional encodings`` if covariances are provided. Each axis is encoded with frequencies r

Enum for camera types.

Enum for camera types.

Camera model

Describes region of space as a frustum.

Identity encoding (Does not modify input)

Sets the nears and fars with fixed values. Args: near_plane: distance to near plane far_plane: distance to far plane

UniSurf Model Config

Sample based on probability distribution Args: num_samples: Number of samples per ray train_stratified: Randomize location within

Calculate depth along ray. Depth Method: - median: Depth is set to the distance where the accumulated weight reaches 0.5. - expec

A bundle of ray parameters.

This is a very primitive struct for holding images, especially for when these images are of different heights / widths. The purpose of this i

Index into embeddings. # TODO: add different types of initializations Args: in_dim: Number of embeddings out_dim: Dimension o

Samples along a ray

Accumulated value along a ray.

Dummy dataclass

A lightweight density field module. Args: aabb: parameters of scene aabb bounds num_layers: number of hidden layers hidde

Standard volumetic rendering. Args: background_color: Background color as RGB. Uses random colors if None.

Contract unbounded space using the contraction was proposed in MipNeRF-360. We use the following contraction equation: .. math::

Camera

Data that corresponds to a single 3D point

RGB output Args: in_dim: input dimension. If not defined in constructor, it must be set later. activation: output head activation

Blender dataset parser config

Density output Args: in_dim: input dimension. If not defined in constructor, it must be set later. activation: output head activa

Basic scheduler config with self-defined exponential decay schedule

NeuS Model Config

Basic optimizer config with RAdam

Compound Field that uses TCNN Args: aabb: parameters of scene aabb bounds num_layers: number of hidden layers hidden_dim:

Timer context manager that calculates duration around wrapped functions

Viewer class for connecting to the bridge server. Args: zmq_port: Where to connect with ZMQ. window: An already existing ViewerWi

VolSDF's error bounded sampler that uses a sdf network to generate samples.

Configuration for data manager instantiation; DataManager is in charge of keeping the train/eval dataparsers; After instantiation, data manager ho

Convenience class to aply the same operation to a whole set of images.

Sample linearly in disparity along a ray Args: num_samples: Number of samples per ray train_stratified: Use stratified sampling d

MLP as used in Vision Transformer, MLP-Mixer and related networks

NeRF Field Args: position_encoding: Position encoder. direction_encoding: Direction encoder. base_mlp_num_layers: Number

Nerfstudio dataset config

NeuS sampler that uses a sdf network to generate samples with fixed variance value in each iterations.

Sampler that uses a proposal network to generate samples.

Basic scheduler config with self-defined exponential decay schedule

Calculate semantics along the ray.

@brief exception indicating access out of the defined range @sa https://json.nlohmann.me/api/basic_json/out_of_range/

Feature Field Config

FeatureSegField Config

Configuration for pipeline instantiation

Stores Gaussians Args: mean: Mean of multivariate Gaussian cov: Covariance of multivariate Gaussian.

Renders the iterations per second for a progress bar.

Spherical harmonic encoding Args: levels: Number of spherical hamonic levels to encode.

Sets the nears and fars with ray-sphere intersection.

Learned vector-matrix encoding proposed by TensoRF Args: resolution: Resolution of grid. num_components: Number of components per

UniSurf Model Config

NeuS sampler that uses a sdf network to generate samples with fixed variance value in each iterations.

Vanilla Model Config

VolSDF Model Config

Module for colliding rays with the scene box to compute near and far values. Args: scene_box: scene box to apply to dataset

Args: dataparser_outputs: description of where and how to read input images.

Collated image dataset that implements caching of default-pytorch-collatable data. Creates batches of the InputDataset return type. Args:

D-NeRF dataset parser config

Optimizable temporal deformation using an MLP. Args: position_encoding: An encoding for the XYZ of distortion temporal_encoding: A

Distilled NeuSFactoModel config

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

Dummy dataclass

Base field output Args: out_dim: output dimension for renderer field_head_name: Field type in_dim: input dimension. If no

Friends dataset parser config

Dataset that returns images, possibly of different sizes. The only thing that separates this from the inputdataset is that this will return i

Data the corresponds to a single image

Interpolation module.

A helper that will allow an instance of a class to return multiple kinds of iterables bound to different functions of that class. To use this