zensvi.transform.VGGTProcessor
==============================

.. py:class:: zensvi.transform.VGGTProcessor(vggt_path: str = 'vggt')

   A class for processing images using VGGT model to generate point clouds.


   .. py:method:: process_images(image_paths: List[str]) -> Dict[str, Any]

      Process images and generate predictions.

      :param image_paths: List of paths to input images

      :returns: Dictionary containing processed predictions



   .. py:method:: generate_point_cloud(predictions: Dict[str, Any]) -> Tuple[numpy.ndarray, numpy.ndarray, numpy.ndarray, numpy.ndarray]

      Generate point cloud from model predictions.

      :param predictions: Dictionary containing model predictions

      :returns: Tuple containing (points, colors, confidence, camera poses)



   .. py:method:: process_images_to_pointcloud(dir_input: Union[str, pathlib.Path], dir_output: Union[str, pathlib.Path], batch_size: int = 1, max_workers: int = 4) -> None

      Process images to generate point clouds using VGGT model.

      :param dir_input: Input directory or file containing images
      :param dir_output: Output directory for point cloud files
      :param batch_size: Batch size for processing
      :param max_workers: Number of worker threads



   .. py:method:: visualize_point_cloud(points: numpy.ndarray, colors_flat: numpy.ndarray, marker_size: int = 1, opacity: float = 0.8, sample_rate: float = 0.1, camera_eye: Optional[Dict[str, float]] = None, camera_up: Optional[Dict[str, float]] = None) -> None

      Visualizes a point cloud using Plotly with random sampling.

      :param points: The point cloud coordinates array.
      :type points: np.ndarray
      :param colors_flat: The colors array for the points.
      :type colors_flat: np.ndarray
      :param marker_size: Size of point markers.
      :type marker_size: int
      :param opacity: Opacity of points.
      :type opacity: float
      :param sample_rate: Percentage of points to sample (0-1).
      :type sample_rate: float
      :param camera_eye: Camera position.
      :type camera_eye: dict
      :param camera_up: Camera up direction.
      :type camera_up: dict