Compute elementwise mean across a list of homogeneous metric dicts.

Print report footer.

Print report header.

Read point cloud from PLY file.

Save GT extrinsics/intrinsics/image_files for evaluation. This is needed when frames are sampled, so eval_pose and fuse3d can use

Common implementation for saving images synchronously or asynchronously

Convert numpy scalars to plain Python floats for JSON safety.

Align all camera poses to the first camera's coordinate frame. Args: camera_poses: Camera poses as SE3 transformations [N, 4, 4]

Pre-cache all example scenes at startup. Args: show_cam: Whether to show camera in visualization filter_blac

Arrange images in a line. The interface resembles a CSS div with flexbox.

Return whether at least ``required_gb`` seems available on the current GPU. The returned tuple is (is_available, message) with a human-friendly m

Apply color to a metric value based on whether it's best/worst. Args: value: String representation of the value is_best: Whe

Compute the average point alignment error (using only original inputs) Args: point_map1: target point map (b, h, w, 3) conf1: target

Compute pose estimation metrics between predicted and ground truth trajectories. Args: pred_se3: Predicted SE(3) transformations [N,

Args: depth1: (n1, h, w) depth2: (n2, h, w) conf1: (n1, h, w) conf2: (n2, h, w)

Args: depth1: (n1, h, w) depth2: (n2, h, w) conf1: (n1, h, w) conf2: (n2, h, w)

Convert metric model state dict to match current model architecture. Args: state_dict: Original metric state dictionary Returns

Create a normalized UV grid of shape (width, height, 2). The grid spans horizontally and vertically according to an aspect ratio, ensuri

Evaluate 3D reconstruction quality against ground truth. Args: scene: Scene identifier fuse_path: Path to fu

Generate a 3D point cloud and camera wireframes and export them as a ``.glb`` file. The function builds a point cloud from the predicted depth ma

Extract image feature descriptors

Convert the extrinsics to a representation with 5 degrees of freedom: 1. Distance from pivot point in the "X" (look cross pivot axis) direction.

Find the 0-based chunk index that contains the given index idx. chunks: List of (begin_idx, end_idx). idx: The index to search for. R

Batch version of weighted least squares Homography src_pts_batch: (B, K, 2) dst_pts_batch: (B, K, 2) confident_weight_batch: (B, K)

Find loop closures

Get scene data including images, camera parameters, and auxiliary info. Args: scene: Scene identifier Returns:

Collect per-view image paths, intrinsics/extrinsics for a scene. Only uses iPhone images (not DSLR). Args: scen

Collect per-view image paths, intrinsics/extrinsics for a scene. Args: scene: Scene identifier (e.g., "chess")

Collect per-view image paths, intrinsics/extrinsics for a scene. Args: scene: Scene path (e.g., "xxx/yyy/zzz")

Collect per-view image paths, intrinsics/extrinsics for a scene. Args: scene: Scene identifier (e.g., "courtyard")

Calculate the frame range centered at idx with half_window frames on each side within chunk boundaries. If near boundaries, take 2 * half

Get paths of all image files in directory

Get backend status information.

Get view data by index, handling bounds. Args: processed_data: Processed data dictionary view_index: Index o

Import a python item. Example: import_item("path.to.file", "MyClass") -> MyClass

Run inference according to requested modes. - Unposed export if 'pose' or 'recon_unposed' is in modes - Posed export if 'rec

Interpolate extrinsics by rotating around their "focus point," which is the least-squares intersection between the look vectors of the initial and

Launch the application. Args: host: Host address to bind to port: Port number to bind to **kwarg

Load a scene from examples directory. Args: scene_name: Name of the scene to load examples_dir: Path to exam

Load all metrics JSON files from a directory. Args: metric_dir: Path to directory containing metric JSON files Returns:

Load model if not already loaded.

This function generates a 1D positional embedding from a given grid using sine and cosine functions. # noqa Args: - embed_dim: The embed

Convert rotations given as rotation matrices to quaternions. Args: matrix: Rotation matrices as tensor of shape (..., 3, 3). Re

Convert rotations given as rotation matrices to quaternions. Args: matrix: Rotation matrices as tensor of shape (..., 3, 3). Re

Navigate measure view. Args: processed_data: Processed data dictionary current_selector: Current selector va

Convert numpy s,R,t to pypose Sim3

Main optimization function Args: sequential_transforms: Input sequence of transforms loop_constraints: List

Optimized vectorized reservoir sampling with batch probability calculations. This maintains mathematical correctness while improving perform

Convert 2D position grid (HxWx2) to sinusoidal embeddings (HxWxC) Args: pos_grid: Tensor of shape (H, W, 2) containing 2D coordinate

Print evaluation metrics in a beautiful tabular format. Args: metrics: Dictionary mapping "dataset_mode" to metric resul

Quaternion Order: XYZW or say ijkr, scalar-last Convert rotations given as quaternions to rotation matrices. Args: quaternions:

Reorder views to place the selected reference view first. Args: x: Input tensor of shape (B, S, N, C) b_idx: Reference v

Compute residuals (modified from original code)

Set sky regions to maximum depth and high confidence. Args: depth: Depth tensor depth_conf: Depth confidence tensor

Start the backend server.

frame: (H,W,D) -> (H,W,3)

Sim(3) transform point cloud points: (N, 3) rot: (3, 3) trans: (3,) or (1, 3) scale: float inverse: Whether to do inverse tra

for np < 2