r"""Function that measures Learned Perceptual Image Patch Similarity (LPIPS). Arguments: x, y (torch.Tensor): the input tensors to co

return a logger for the requested format :param _format: the requested format to log to ('stdout', 'log', 'json' or 'csv' or 'tensorboard')

r"""Normalizes a quaternion to unit norm. Args: quaternion (torch.Tensor): Quaternion to normalize (shape: :math:`(4)`) (Assu

Get any orthogonal vector in 3D space

Post-process a mesh to filter out floaters and disconnected parts

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

Taken from https://github.com/colmap/colmap/blob/dev/scripts/python/read_write_model.py

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

Taken from https://github.com/colmap/colmap/blob/dev/scripts/python/read_write_model.py

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

Render the scene. Background tensor (bg_color) must be on GPU!

Transforms poses so principal components lie on XYZ axes. Args: poses: a (N, 3, 4) array containing the cameras' camera to world transforms.

Learning rate scheduling per step

Write the sequence of args, with no separators, to the console and output files (if you've configured an output file). Using

write_sequence an array to file :param sequence:

r"""Converts a quaternion to a :math:`3 \times 3` rotation matrix. Args: quaternion (torch.Tensor): Quaternion to convert (shape: :math:`

log to a file, in a human readable format :param filename_or_file: the file to write the log to :param max_length: the maximu

Dumps key/value pairs into TensorBoard's numeric format. :param folder: the folder to write the log to

b :param path: Path to colmap scene main folder.