! @brief post-decrement (it--) @pre The iterator is initialized; i.e. `m_object != nullptr`. */

Learn PCA whitening with shrinkage from given descriptors

@brief remove last reference token @sa https://json.nlohmann.me/api/json_pointer/pop_back/

Converts VGGT predictions to a 3D scene represented as a GLB file. Args: predictions (dict): Dictionary containing model predictions

Sets the current viewing frame Args: frame: image to be viewed

Return quaternion from rotation matrix. Args: matrix: rotation matrix to obtain quaternion isprecise: if True, input matrix is as

Qeury the feature field

Parse COLMAP cameras.bin file into a dictionary of Camera objects. Args: path_to_model_file: Path to cameras.bin file. Returns:

Parse COLMAP images.bin file into a dictionary of Image objects. Args: path_to_model_file: Path to images.bin file. Returns:

see: src/base/reconstruction.cc void Reconstruction::ReadPoints3DBinary(const std::string& path) void Reconstruction::WritePoints

Async method to grab and wait on frame

extract 3D points from prediction head output

reset token_buffer; current character is beginning of token

Convert quaternion rotation and translation vectors to 4x4 matrix

Runs the callback if it's supposed to be run at the given location. Args: step: current iteration step location: when

Sample a random viewpoint using the navmesh

property: screenSize

Set the anneal value for the proposal network.

Set the number of rays to sample per batch. Args: num_rays_per_batch: number of rays to sample per batch

Sets offsets for this frustum for computing positions

Returns the instantiated object using the config.

This function disables printing when not in master process

@brief returns the number of elements @sa https://json.nlohmann.me/api/basic_json/size/

Returns the focal length of a three.js perspective camera. Args: fov: the field of view of the camera in degrees. image_height: t

Applies a 4x4 transformation to a set of points. Args: transformation (np.ndarray): Transformation matrix. points (np.ndarra

Return ndarray normalized by length, i.e. Euclidean norm, along axis. Args: axis: the axis along which to normalize into unit vector

update the profiler dictionary with running averages of durations Args: func_name: the function name that is being profiled

Upsamples underyling feature grid Args: resolution: Target resolution.

method: waitUntilCompleted

! @param[in] j JSON value to serialize @pre j.type() == value_t::object */

! @param[in] j JSON value to serialize */

! @param[in] j JSON value to serialize */

Output a (H,W,2) array of int32 with output[j,i,0] = i + origin[0] output[j,i,1] = j + origin[1]