pack and write to a binary file. :param fid: :param data: data to send, if multiple elements are sent at the same time, they should be enc

Read and unpack the next bytes from a binary file. :param fid: :param num_bytes: Sum of combination of {2, 4, 8}, e.g. 2, 6, 16, 30, etc.

Compute keypoints, scores, descriptors for image

Return a path to image

Adjust learning rate based on epoch. Optional: call this function if keep training the model after loading checkpoint

get uncertainty and remove point with high uncertainty args: points3D: numpy array (1, 4, N) return: points3D (N, 3)

Load regressor checkpoint from path

convert a list of line3D objects to an Open3D lines set Args: lines (list[:class:`datasets._base.Line3D`] or numpy array of Nx6): The

convert a numpy array of points3D to an Open3D lines set Args: points (numpy array of Nx3): The 3D point map color (list[floa

Interpolate descriptors at keypoint locations

A training/validation step.

Read an image, preprocess it, and Return a keypoints from that image using loaded point detector model.

Return a pose vector [tvec, qvec]

(use only for point2d detector model) Read an image, do augmentation if needed, preprocess it, and return a dictionary of im

Visualize a 3D line map with `Open3D <http://www.open3d.org/>`_ Args: lines (list[:class:`datasets._base.Line3D` and/or None]): The

Visualize a 3D point map with `Open3D <http://www.open3d.org/>`_ Args: points3D (list[:class:`datasets._base.Line3D` and/or None]):

To be implemented by child class.

To be implemented by child class.

Creating same inputs for limap library and estimate camera pose

Check if the files exist, if yes, remove them

Create axis, plane and pyramed geometries in Open3D format. :param K: calibration matrix (camera intrinsics) :param R: rotation matrix :pa

Evaluate the estimated poses with ground truth poses args: spath: path to save the estimated poses and ground truth poses mo

get uncertainty and remove point with high uncertainty args: points3D: numpy array (1, 4, N) return: points3D (N, 3)

Return a camera vector from a colmap camera object return: numpy array of camera vector [modelid, width, height, foca

Get the class object which inherits from BaseClass and is defined in the module named mod_name, child of base_path.

Return a dictionary of camera

Return a point detector model

Get a point detector

Return a pose matrix [R|t]

Removes keypoints too close to the border

Save 3D line map with `Open3D <http://www.open3d.org/>`_ Args: lines3D: numpy array of Nx6 hightlight_lines3D: numpy array o

Save 3D point map with `Open3D <http://www.open3d.org/>`_ Args: points3D (list[:class:`datasets._base.Line3D` and/or None]): The 3D

Evaluate the estimated poses with ground truth poses args: eval_cfg: evaluation config spath: path to save the estimated pose

gt_pt2Ds: 2xN pt3Ds: 3xN c_pose: 1x7 camera: 1x5 valids: 1xN

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

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

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

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

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

see: src/base/reconstruction.cc void Reconstruction::ReadPoints3DText(const std::string& path) void Reconstruction::WritePoints3D