Invert a torch or numpy matrix

property: line

method: pushDebugGroup:

return value of the iterator

method: commit

Returns the device that the camera is on.

Get the file id from the google drive zip url.

Convert path object to serializable format

! @brief public parser interface @param[in] strict whether to expect the last token to be EOF @param[in,out] result parsed JSON val

property: status

Converts a depth map to a color image. Args: value (torch.Tensor, numpy.ndarry): Input depth map. Shape: (H, W) or (1, H, W) or (1, 1, H,

Shared setup for loading a saved pipeline for evaluation. Args: config_path: Path to config YAML file. eval_num_rays_per_chunk: N

Run forward starting with a ray bundle. This outputs different things depending on the configuration of the model and whether or not the batch

method: init

@brief return whether value is a binary array @sa https://json.nlohmann.me/api/basic_json/is_binary/

Load a dictionary from a JSON filename. Args: filename: The filename to load from.

A context manager that does nothing is verbose is True. Otherwise it hides logs under a message. Args: msg: The message to log. s

! @brief returns x - y @pre x.e == y.e and x.f >= y.f */

! @brief get next character from the input This function provides the interface to the used input adapter. It does not throw in case the

Given three 2D points, return the area defined by the parallelogram. I.e., 2x the triangle area. Args: p: The origin of the parallelogram

Get the param groups for the pipeline. Returns: A list of dictionaries containing the pipeline's param groups.

Calulates "start" position of frustum. We use start positions for MonoSDF because when we use error bounded sampling, we need to upsample many

Returns hash tensor using method described in Instant-NGP Args: in_tensor: Tensor to be hashed

Returns hash tensor using method described in Instant-NGP Args: in_tensor: Tensor to be hashed

open and convert all images in a list or folder to proper input format for DUSt3R

method: setVertexBuffer:offset:atIndex:

Train the model.

property: width

image has B x 3 x img_size x img_size do_mask: whether to perform masking or not return_all_blocks: if True, return the feat

Returns the dataparser outputs for the given split. Args: split: Which dataset split to generate (train/test). Returns:

return current variance value

@brief exchanges the values @sa https://json.nlohmann.me/api/basic_json/swap/

Method to convert mutable dict to default factory dict Args: d: dictionary to convert into default factory dict for dataclass

method: contents

Download the D-NeRF dataset (https://github.com/albertpumarola/D-NeRF).

method: endEncoding

return current beta value

Takes in camera parameters and computes the output of the model. Args: camera_ray_bundle: ray bundle to calculate outputs over

Return weights based on predicted alphas Args: alphas: Predicted alphas (maybe from sdf) for samples along ray Returns:

Invert provided pose matrix. Args: pose: Camera pose without homogenous coordinate. Returns: Inverse of pose.

@brief return whether value is a string @sa https://json.nlohmann.me/api/basic_json/is_string/

@brief create JSON pointer @sa https://json.nlohmann.me/api/json_pointer/json_pointer/

Cull mesh by rendering the segmentation of each face.

More info here: https://arxiv.org/pdf/2206.00665.pdf supplementary section A2 Depth Consistency Loss This function computes scale/shift requi

@brief append an unescaped token at the end of the reference pointer @sa https://json.nlohmann.me/api/json_pointer/push_back/

Rescale the output resolution of the cameras. Args: scaling_factor: Scaling factor to apply to the output resolution.