Fully connected ResNet Block class. Args: size_in (int): input dimension size_out (int): output dimension size_h (int):

`UNet` class is based on https://arxiv.org/abs/1505.04597 The U-Net is a convolutional encoder-decoder neural network. Contextual spatial in

CheckpointIO class. It handles saving and loading checkpoints. Args: checkpoint_dir (str): path where checkpoints are saved

A helper Module that performs 2 convolutions and 1 MaxPool. A ReLU activation follows each convolution.

Helper class for launching OmniKit from a Python environment. Launches and configures OmniKit and exposes useful functions. Typical usag

A helper Module that performs 2 convolutions and 1 UpConvolution. A ReLU activation follows each convolution.

Positional Encoding (presented in NeRF) Args: basis_function (str): basis function

Global Variables & Strctures

Base trainer class.

Decoder. Instead of conditioning on global features, on plane/volume local features. Args: dim (int): input dimension c_

Occupancy Network class. Args: decoder (nn.Module): decoder network encoder (nn.Module): encoder network device (device)

Generator class for Occupancy Networks. It provides functions to generate the final mesh as well refining options. Args: model (nn

Decoder. Instead of conditioning on global features, on plane/volume local features. Args: dim (int): input dimension c_

PointNet-based encoder network with ResNet blocks for each point. Number of input points are fixed. Args: c_dim (int): dimen

Trainer object for the Occupancy Network. Args: model (nn.Module): Occupancy Network model optimizer (optimizer): pytorch optimi

Point cloud noise transformation class. It adds noise to point cloud data. Args: stddev (int): standard deviation

Point cloud subsampling transformation class. It subsamples the point cloud data. Args: N (int): number of points to be subsampled

Points subsampling transformation class. It subsamples the points data. Args: N (int): number of points to be subsampled

Add new keys to the given input Args: s (float): the defined voxel size pos_encoding (str): method for the positional encoding,