Applies a function to all fields of the tensor dataclass. TODO: Someone needs to make a high level design choice for whether not not we want

property: arrayLength

Blur a bilateral-space vector with a 1 2 1 kernel in each dimension

@brief returns an iterator to one past the last element @sa https://json.nlohmann.me/api/basic_json/cend/

Delete data.

Args: - depthmap (HxW array): - camera_intrinsics: a 3x3 matrix - camera_pose: a 4x3 or 4x4 cam2world matrix Returns:

std::istream/std::streambuf use std::char_traits<char>::to_int_type, to ensure that std::char_traits<char>::eof() and the character 0xFF do not end up

Get a Mesh from a filename.

Return normalized positions in range [0, 1] based on the aabb axis-aligned bounding box. Args: positions: the xyz positions

Helper function to return a rich Progress object.

property: height

return whether the iterator can be dereferenced

property: length

Returns the unwrapped model if in ddp

! @brief returns x * y @note The result is rounded. (Only the upper q bits are returned.) */

Returns a normalized vector.

Show data transfer speed.

Run function that checks to see if any of the existing state has changed (e.g. camera pose/output type/resolutions). Sets the viewer s

Sample an image batch and return a pixel batch. Args: image_batch: batch of images to sample from step: current train

Returns true based on current step and step interval.

Parses the input focal length / principle point x or y and returns a tensor of the correct shape Only needs to make sure that we a 1

! @brief public accept interface @param[in] strict whether to expect the last token to be EOF @return whether the input is a proper JSON

Return a 3D point cloud corresponding to valid pixels of the depth map

@brief return whether pointer points to the root document @sa https://json.nlohmann.me/api/json_pointer/empty/

Args: color (Union[str, list]): Color as a string or a rgb list Returns: TensorType[3]: Parsed color

Computes and returns the densities. Returns a tensor of densities and a tensor of features. Args: ray_samples: Samples locations

This gets the image coordinates of one of the cameras in this object. If no index is specified, it will return the maximum possible sized hei

Returns the intrinsic matrices for each camera. Returns: Pinhole camera intrinsics matrices

Returns the number of frames in a video. Args: video: Path to a video. Returns: The number of frames in a video.

Produces samples for each ray by projection points along the ray direction. Currently samples uniformly. Args: bin_starts: Distan

Return weights and transmittance based on predicted densities Args: densities: Predicted densities for samples along ray

Initialize parts of decoder that are dependent on dimension of encoder tokens. Should be called when setting up MultiMAE. :p

Calculates the proposal loss in the MipNeRF-360 paper. https://github.com/kakaobrain/NeRF-Factory/blob/f61bb8744a5cb4820a4d968fb3bfbed777550f4a/s

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

Returns True if distributed is available and initialized.

Checks if a viewer is enabled.

Generic method iterating through a base_path folder to find scenes.

Merge two set of ray samples and return sorted index which can be used to merge sdf values Args: ray_samples_1 : ray_samples to m

method: newBufferWithLength:options:

Returns the next batch of data from the train data manager. This will be a tuple of all the information that this data manager outputs.

renorm pointmaps pts1, pts2 with norm_mode