nerfbaselines.datasets

nerfbaselines.datasets.dataset_index_select(dataset: TDataset, i: slice | list | ndarray) → TDataset

nerfbaselines.datasets.dataset_load_features(dataset: UnloadedDataset, features=None, supported_camera_models=None) → Dataset

nerfbaselines.datasets.download_dataset(path: str, output: str | Path)

nerfbaselines.datasets.load_dataset(path: Path | str, split: str, features: FrozenSet[Literal['color', 'points3D_xyz', 'points3D_rgb', 'images_points3D_indices']] | None = None, supported_camera_models: FrozenSet[Literal['pinhole', 'opencv', 'opencv_fisheye', 'full_opencv']] | None = None, load_features: bool = True, **kwargs) → Dataset | UnloadedDataset

nerfbaselines.datasets.blender

nerfbaselines.datasets.blender.download_blender_dataset(path: str, output: str) → None

nerfbaselines.datasets.blender.load_blender_dataset(path: str, split: str, **kwargs)

Load a Blender dataset (scenes: lego, ship, drums, hotdog, materials, mic, chair, ficus).

Parameters:

• path – Path to the dataset directory.

• split – The split to load, either ‘train’ or ‘test’.

Returns:

Unloaded dataset dictionary.

nerfbaselines.datasets.bundler

nerfbaselines.datasets.bundler.load_bundler_dataset(path: str, split: str | None = None, images_path: str | None = None, features: FrozenSet[Literal['color', 'points3D_xyz', 'points3D_rgb', 'images_points3D_indices']] | None = None, bundler_file: str = 'cameras.out', attributes: str | Tuple[str, ...] = ('f', 'cx', 'cy'), camera_model: str | None = None, coordinate_system: Literal['opengl', 'opencv'] = 'opengl', sampling_masks_path: str | None = None)

nerfbaselines.datasets.colmap

nerfbaselines.datasets.colmap.load_colmap_dataset(path: Path | str, split: str | None = None, *, test_indices: Indices | None = None, features: FrozenSet[Literal['color', 'points3D_xyz', 'points3D_rgb', 'images_points3D_indices']] | None = None, images_path: Path | str | None = None, colmap_path: Path | str | None = None, sampling_masks_path: Path | str | None = None)

nerfbaselines.datasets.llff

nerfbaselines.datasets.llff.download_llff_dataset(path: str, output: str) → None

nerfbaselines.datasets.llff.load_llff_dataset(path: Path | str, split: str, *, downscale_factor: int = 4, **_)

nerfbaselines.datasets.mipnerf360

nerfbaselines.datasets.mipnerf360.download_mipnerf360_dataset(path: str, output: Path | str)

nerfbaselines.datasets.nerfonthego

nerfbaselines.datasets.nerfonthego.load_nerfonthego_dataset(path: str, split: str, **kwargs) → UnloadedDataset

nerfbaselines.datasets.nerfstudio

nerfbaselines.datasets.nerfstudio.download_nerfstudio_dataset(path: str, output: str)

Download data in the Nerfstudio format. If you are interested in the Nerfstudio Dataset subset from the SIGGRAPH 2023 paper, you can obtain that by using –capture-name nerfstudio-dataset or by visiting Google Drive directly at: https://drive.google.com/drive/folders/19TV6kdVGcmg3cGZ1bNIUnBBMD-iQjRbG?usp=drive_link.

nerfbaselines.datasets.nerfstudio.load_nerfstudio_dataset(path: Path | str, split: str, downscale_factor: int | None = None, features: FrozenSet[Literal['color', 'points3D_xyz', 'points3D_rgb', 'images_points3D_indices']] | None = None, **kwargs)

nerfbaselines.datasets.phototourism

class nerfbaselines.datasets.phototourism.NerfWEvaluationProtocol

Bases: EvaluationProtocol

accumulate_metrics(metrics: Iterable[Dict[str, float | int]]) → Dict[str, float | int]

evaluate(predictions: Dict[str, ndarray], dataset: Dataset) → Dict[str, float | int]

get_name()

render(method: Method, dataset: Dataset, *, options=None) → Dict[str, ndarray]

nerfbaselines.datasets.phototourism.download_phototourism_dataset(path: str, output: str)

nerfbaselines.datasets.seathru_nerf

nerfbaselines.datasets.seathru_nerf.download_seathru_nerf_dataset(path: str, output: str)

nerfbaselines.datasets.seathru_nerf.load_seathru_nerf_dataset(path: str, split: str | None, **kwargs)

nerfbaselines.datasets.tanksandtemples

nerfbaselines.datasets.tanksandtemples.download_tanksandtemples_dataset(path: str, output: str) → None