Configure a logger. Adapted from Detectron2. Args: name: The name of the logger to configure. level: The logging level

Generate the indices of a random permutation.

r"""Preprocesses the color image by resizing to :math:`(H, W, C)`, (optionally) normalizing values to :math:`[0, 1]`, and (optionally) using c

r"""Preprocesses the depth image by resizing, adding channel dimension, and scaling values to meters. Optionally converts depth from channels

r"""Preprocesses the poses by setting first pose in a sequence to identity and computing the relative homogenous transformation for all other

This function disables printing when not in the main process

Returns torch.sqrt(torch.max(0, x)) but with a zero subgradient where x is 0. Source: https://pytorch3d.readthedocs.io/en/latest/_modules

Align two trajectories using the method of Horn (closed-form). Args: model -- first trajectory (3xn) data -- second trajectory (3

mIoU

PixAcc

r"""Transforms coordinates from the camera frame to the pixel frame. # based on # https://github.com/ClementPinard/SfmLearner-Pytorch/blob/ma

Check if points can be projected into the camera view. Returns: bool: True if there are points can be projected

r"""Compose two homogeneous 3D transforms. Args: trans1 (torch.Tensor): first transformation (shape: :math:`* \times 4 \times

r"""Generates a coordinate grid for an image. When `normalized_coords` is set to True, the grid is normalized to be in the range [-1, 1] (to

Implements the "standard" process for log regression evaluation: The value of C is chosen by training on train_dataset and evaluating on

x_list contains a list of tensors to nest together and run