Align `depth_src` to `depth_tgt` with given constant weights. ### Parameters: - `depth_src: torch.Tensor` of shape (..., N) - `depth

Align `depth_src` to `depth_tgt` with given constant weights. ### Parameters: - `depth_src: torch.Tensor` of shape (..., N) - `dept

### Parameters: - `points_src: torch.Tensor` of shape (..., N, 3) - `points_tgt: torch.Tensor` of shape (..., N, 3) - `weight: torch.

Align `points_src` to `points_tgt` with respect to a shared xyz scale and z shift. It is similar to `align_affine` but scale and shift are a

Align `points_src` to `points_tgt` with respect to a shared xyz scale and z shift. It is similar to `align_affine` but scale and shift are a

Align `points_src` to `points_tgt` with respect to a shared xyz scale and z shift. It is similar to `align_affine` but scale and shift are a

Align `points_src` to `points_tgt` with respect to a Z-axis shift. ### Parameters: - `points_src: torch.Tensor` of shape (..., N, 3)

world_tracks: 1 1 K 3 this is the coarse 3d tracks in world coordinate (coarse 3d tracks) intrs: B T 3 3 this is the intrinsic matrix

Bake texture to a mesh from multiple observations. Args: vertices (np.array): Vertices of the mesh. Shape (V, 3). faces (np.

Bake texture to a mesh from multiple observations. Args: vertices (np.array): Vertices of the mesh. Shape (V, 3). faces (np.

Convert Batched Pytorch Tensors to PyCOLMAP Check https://github.com/colmap/pycolmap for more details about its format

Render rays in smaller minibatches to avoid OOM.

Convert an array of binary values into Gray codes. This uses the classic X ^ (X >> 1) trick to compute the Gray code. Parameters: ------

Transform normal from world space to camera space. :param normal: The normal in world space. :param c2w: The camera to world matrix.

Return the attention configuration of the model.

Return the attention configuration of the model.

Calculate Boundary F1 score. Args: ---- pr (np.ndarray): Predicted depth matrix. gt (np.ndarray): Ground truth depth matrix.

Build the model from the config NOTE: the config should contain the following - encoder: the encoder type of the model

Generates point grids for all crop layers.

Generates a 2D grid of points evenly spaced in [0,1]x[0,1].

Calculate serialization and partitioning for a set of coordinates. Args: tensor (SparseTensor): The input tensor. window_siz

Calculate serialization and partitioning for a set of coordinates. Args: tensor (SparseTensor): The input tensor. window_siz

Calculate serialization and partitioning for a set of coordinates. Args: tensor (SparseTensor): The input tensor. window_siz

Calculate serialization and partitioning for a set of coordinates. Args: tensor (SparseTensor): The input tensor. window_siz

从二值化掩码中计算边界框 :param binary_mask: 二维numpy数组，表示二值化掩码 :return: 边界框 (xmin, ymin, width, height)

Computes the inverse of each 4x4 SE3 matrix in the batch. Args: - se3 (Tensor): Nx4x4 tensor of SE3 matrices. Returns: - Tensor

Compute the inverse of each 4x4 (or 3x4) SE3 matrix in a batch. If `R` and `T` are provided, they must correspond to the rotation and transl

Map (x, y) -> color in (R, G, B). 1) Normalize x,y to [0,1]. 2) Combine them into a single scalar c in [0,1]. 3) Use matplotlib's col

Computes average precision for given ranked indexes. Arguments --------- ranks : zerro-based ranks of positive images nres : num

Compute metrics for 'pred' compared to 'gt' Args: gt (numpy.ndarray): Ground truth values pred (numpy.ndarray): Predicted values

根据相机内参矩阵 K 和图像尺寸计算 FoV 参数: K (np.ndarray): 3x3 相机内参矩阵 width (int): 图像宽度（像素） height (int): 图像高度（像素） degrees (bool): 是否返回角

@cam_in_world: (4,4) in normalized space @rays: (...,D) in camera Return: (-1,D+2) with near far

adapted from https://github.com/amyxlase/relpose-plus-plus

Compute the weighted standard deviation of 2D tracks across time. Args: track2d (Tensor): shape (B, T, N, 2), 2D tracked points.

Add new points and labels to previous point inputs (add at the end).

Find connected components in the given row and column indices. Args: ---- r (np.ndarray): Row indices. c (np.ndarray): Column

construct a dense grid based on resolution

将给定路径列表中的单通道深度图归一化到 0~255 并转为三通道，组成视频保存 :param file_paths: 包含所有深度图文件路径的列表 :param output_video_path: 输出视频文件的路径 :param fps: 输出视频的帧

Convert the torso of the model to bfloat16.

Convert the torso of the model to float16.

Convert the torso of the model to bfloat16.

Convert the torso of the model to bfloat16.

Convert the torso of the model to bfloat16.

Convert the torso of the model to float16.

Convert the torso of the model to float16.

Convert the torso of the model to float16.

Convert the torso of the model to float16.

Convert the torso of the model to float16.

Convert the torso of the model to float16.

Convert the torso of the model to float16.

Convert the torso of the model to float16.

Convert the torso of the model to float16.

Convert the torso of the model to float16.

Convert the torso of the model to float16.

Convert the torso of the model to float16.

Convert the torso of the model to float32.

Converts all objects in the scene to meshes. Returns: None

Instead of storing the entire correlation pyramid, we compute each level's correlation volume, sample it immediately, then discard it

Creates a intri matrix from focal length and principal point. Args: focal_length (torch.Tensor): A Bx2 or BxSx2 tensor containing th

Create a DepthPro model and load weights from `config.checkpoint_uri`. Args: ---- config: The configuration for the DPT model archite

Instantiate NeRF's MLP model.