scannet_dataset.py

# Copyright (c) OpenMMLab. All rights reserved.
import warnings
from os import path as osp
from typing import Callable, List, Optional, Union

import numpy as np

from mmdet3d.core import show_result
from mmdet3d.core.bbox import DepthInstance3DBoxes
from mmdet3d.registry import DATASETS
from .det3d_dataset import Det3DDataset
from .pipelines import Compose
from .seg3d_dataset import Seg3DDataset


@DATASETS.register_module()
class ScanNetDataset(Det3DDataset):
    r"""ScanNet Dataset for Detection Task.

    This class serves as the API for experiments on the ScanNet Dataset.

    Please refer to the `github repo <https://github.com/ScanNet/ScanNet>`_
    for data downloading.

    Args:
        data_root (str): Path of dataset root.
        ann_file (str): Path of annotation file.
        metainfo (dict, optional): Meta information for dataset, such as class
            information. Defaults to None.
        data_prefix (dict): Prefix for data. Defaults to
            `dict(pts='points',
                pts_isntance_mask='instance_mask',
                pts_semantic_mask='semantic_mask')`.
        pipeline (list[dict]): Pipeline used for data processing.
            Defaults to None.
        modality (dict): Modality to specify the sensor data used
            as input. Defaults to None.
        box_type_3d (str): Type of 3D box of this dataset.
            Based on the `box_type_3d`, the dataset will encapsulate the box
            to its original format then converted them to `box_type_3d`.
            Defaults to 'Depth' in this dataset. Available options includes

            - 'LiDAR': Box in LiDAR coordinates.
            - 'Depth': Box in depth coordinates, usually for indoor dataset.
            - 'Camera': Box in camera coordinates.
        filter_empty_gt (bool): Whether to filter empty GT.
            Defaults to True.
        test_mode (bool): Whether the dataset is in test mode.
            Defaults to False.
    """
    METAINFO = {
        'CLASSES':
        ('cabinet', 'bed', 'chair', 'sofa', 'table', 'door', 'window',
         'bookshelf', 'picture', 'counter', 'desk', 'curtain', 'refrigerator',
         'showercurtrain', 'toilet', 'sink', 'bathtub', 'garbagebin')
    }

    def __init__(self,
                 data_root: str,
                 ann_file: str,
                 metainfo: dict = None,
                 data_prefix: dict = dict(
                     pts='points',
                     pts_instance_mask='instance_mask',
                     pts_semantic_mask='semantic_mask'),
                 pipeline: List[Union[dict, Callable]] = [],
                 modality=dict(use_camera=False, use_lidar=True),
                 box_type_3d: str = 'Depth',
                 filter_empty_gt: bool = True,
                 test_mode: bool = False,
                 **kwargs):
        super().__init__(
            data_root=data_root,
            ann_file=ann_file,
            metainfo=metainfo,
            data_prefix=data_prefix,
            pipeline=pipeline,
            modality=modality,
            box_type_3d=box_type_3d,
            filter_empty_gt=filter_empty_gt,
            test_mode=test_mode,
            **kwargs)
        assert 'use_camera' in self.modality and \
               'use_lidar' in self.modality
        assert self.modality['use_camera'] or self.modality['use_lidar']

    @staticmethod
    def _get_axis_align_matrix(info: dict) -> dict:
        """Get axis_align_matrix from info. If not exist, return identity mat.

        Args:
            info (dict): Info of a single sample data.

        Returns:
            np.ndarray: 4x4 transformation matrix.
        """
        if 'axis_align_matrix' in info:
            return np.array(info['axis_align_matrix'])
        else:
            warnings.warn(
                'axis_align_matrix is not found in ScanNet data info, please '
                'use new pre-process scripts to re-generate ScanNet data')
            return np.eye(4).astype(np.float32)

    def parse_data_info(self, info: dict) -> dict:
        """Process the raw data info.

        The only difference with it in `Det3DDataset`
        is the specific process for `axis_align_matrix'.

        Args:
            info (dict): Raw info dict.

        Returns:
            dict: Data information that will be passed to the data
            preprocessing pipelines. It includes the following keys:
        """
        info['axis_align_matrix'] = self._get_axis_align_matrix(info)
        info['pts_instance_mask_path'] = osp.join(
            self.data_prefix.get('pts_instance_mask', ''),
            info['pts_instance_mask_path'])
        info['pts_semantic_mask_path'] = osp.join(
            self.data_prefix.get('pts_semantic_mask', ''),
            info['pts_semantic_mask_path'])

        info = super().parse_data_info(info)
        return info

    def parse_ann_info(self, info: dict) -> dict:
        """Process the `instances` in data info to `ann_info`

        Args:
            info (dict): Info dict.

        Returns:
            dict: Processed `ann_info`
        """
        ann_info = super().parse_ann_info(info)
        # empty gt
        if ann_info is None:
            ann_info['gt_bboxes_3d'] = np.zeros((0, 6), dtype=np.float32)
            ann_info['gt_labels_3d'] = np.zeros((0, ), dtype=np.int64)
        # to target box structure

        ann_info['gt_bboxes_3d'] = DepthInstance3DBoxes(
            ann_info['gt_bboxes_3d'],
            box_dim=ann_info['gt_bboxes_3d'].shape[-1],
            with_yaw=False,
            origin=(0.5, 0.5, 0.5)).convert_to(self.box_mode_3d)

        return ann_info

    def _build_default_pipeline(self):
        """Build the default pipeline for this dataset."""
        pipeline = [
            dict(
                type='LoadPointsFromFile',
                coord_type='DEPTH',
                shift_height=False,
                load_dim=6,
                use_dim=[0, 1, 2]),
            dict(type='GlobalAlignment', rotation_axis=2),
            dict(
                type='DefaultFormatBundle3D',
                class_names=self.CLASSES,
                with_label=False),
            dict(type='Collect3D', keys=['points'])
        ]
        return Compose(pipeline)

    def show(self, results, out_dir, show=True, pipeline=None):
        """Results visualization.

        Args:
            results (list[dict]): List of bounding boxes results.
            out_dir (str): Output directory of visualization result.
            show (bool): Visualize the results online.
            pipeline (list[dict], optional): raw data loading for showing.
                Default: None.
        """
        assert out_dir is not None, 'Expect out_dir, got none.'
        pipeline = self._get_pipeline(pipeline)
        for i, result in enumerate(results):
            data_info = self.get_data_info[i]
            pts_path = data_info['lidar_points']['lidar_path']
            file_name = osp.split(pts_path)[-1].split('.')[0]
            points = self._extract_data(i, pipeline, 'points').numpy()
            gt_bboxes = self.get_ann_info(i)['gt_bboxes_3d'].tensor.numpy()
            pred_bboxes = result['boxes_3d'].tensor.numpy()
            show_result(points, gt_bboxes, pred_bboxes, out_dir, file_name,
                        show)


@DATASETS.register_module()
class ScanNetSegDataset(Seg3DDataset):
    r"""ScanNet Dataset for Semantic Segmentation Task.

    This class serves as the API for experiments on the ScanNet Dataset.

    Please refer to the `github repo <https://github.com/ScanNet/ScanNet>`_
    for data downloading.

    Args:
        data_root (str): Path of dataset root.
        ann_file (str): Path of annotation file.
        pipeline (list[dict], optional): Pipeline used for data processing.
            Defaults to None.
        classes (tuple[str], optional): Classes used in the dataset.
            Defaults to None.
        palette (list[list[int]], optional): The palette of segmentation map.
            Defaults to None.
        modality (dict, optional): Modality to specify the sensor data used
            as input. Defaults to None.
        test_mode (bool, optional): Whether the dataset is in test mode.
            Defaults to False.
        ignore_index (int, optional): The label index to be ignored, e.g.
            unannotated points. If None is given, set to len(self.CLASSES).
            Defaults to None.
        scene_idxs (np.ndarray | str, optional): Precomputed index to load
            data. For scenes with many points, we may sample it several times.
            Defaults to None.
    """
    METAINFO = {
        'CLASSES':
        ('wall', 'floor', 'cabinet', 'bed', 'chair', 'sofa', 'table', 'door',
         'window', 'bookshelf', 'picture', 'counter', 'desk', 'curtain',
         'refrigerator', 'showercurtrain', 'toilet', 'sink', 'bathtub',
         'otherfurniture'),
        'PALETTE': [
            [174, 199, 232],
            [152, 223, 138],
            [31, 119, 180],
            [255, 187, 120],
            [188, 189, 34],
            [140, 86, 75],
            [255, 152, 150],
            [214, 39, 40],
            [197, 176, 213],
            [148, 103, 189],
            [196, 156, 148],
            [23, 190, 207],
            [247, 182, 210],
            [219, 219, 141],
            [255, 127, 14],
            [158, 218, 229],
            [44, 160, 44],
            [112, 128, 144],
            [227, 119, 194],
            [82, 84, 163],
        ],
        'valid_class_ids': (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 14, 16, 24,
                            28, 33, 34, 36, 39),
        'all_class_ids':
        tuple(range(41)),
    }

    def __init__(self,
                 data_root: Optional[str] = None,
                 ann_file: str = '',
                 metainfo: Optional[dict] = None,
                 data_prefix: dict = dict(
                     pts='points', img='', instance_mask='', semantic_mask=''),
                 pipeline: List[Union[dict, Callable]] = [],
                 modality: dict = dict(use_lidar=True, use_camera=False),
                 ignore_index=None,
                 scene_idxs=None,
                 test_mode=False,
                 **kwargs) -> None:
        super().__init__(
            data_root=data_root,
            ann_file=ann_file,
            metainfo=metainfo,
            data_prefix=data_prefix,
            pipeline=pipeline,
            modality=modality,
            ignore_index=ignore_index,
            scene_idxs=scene_idxs,
            test_mode=test_mode,
            **kwargs)

    def get_scene_idxs(self, scene_idxs):
        """Compute scene_idxs for data sampling.

        We sample more times for scenes with more points.
        """
        # when testing, we load one whole scene every time
        if not self.test_mode and scene_idxs is None:
            raise NotImplementedError(
                'please provide re-sampled scene indexes for training')

        return super().get_scene_idxs(scene_idxs)


@DATASETS.register_module()
class ScanNetInstanceSegDataset(Seg3DDataset):

    METAINFO = {
        'CLASSES':
        ('cabinet', 'bed', 'chair', 'sofa', 'table', 'door', 'window',
         'bookshelf', 'picture', 'counter', 'desk', 'curtain', 'refrigerator',
         'showercurtrain', 'toilet', 'sink', 'bathtub', 'garbagebin'),
        'PLATTE': [
            [174, 199, 232],
            [152, 223, 138],
            [31, 119, 180],
            [255, 187, 120],
            [188, 189, 34],
            [140, 86, 75],
            [255, 152, 150],
            [214, 39, 40],
            [197, 176, 213],
            [148, 103, 189],
            [196, 156, 148],
            [23, 190, 207],
            [247, 182, 210],
            [219, 219, 141],
            [255, 127, 14],
            [158, 218, 229],
            [44, 160, 44],
            [112, 128, 144],
            [227, 119, 194],
            [82, 84, 163],
        ],
        'valid_class_ids':
        (3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 14, 16, 24, 28, 33, 34, 36, 39),
        'all_class_ids':
        tuple(range(41))
    }

    def __init__(self,
                 data_root: Optional[str] = None,
                 ann_file: str = '',
                 metainfo: Optional[dict] = None,
                 data_prefix: dict = dict(
                     pts='points', img='', instance_mask='', semantic_mask=''),
                 pipeline: List[Union[dict, Callable]] = [],
                 modality: dict = dict(use_lidar=True, use_camera=False),
                 test_mode=False,
                 ignore_index=None,
                 scene_idxs=None,
                 file_client_args=dict(backend='disk'),
                 **kwargs) -> None:
        super().__init__(
            data_root=data_root,
            ann_file=ann_file,
            metainfo=metainfo,
            pipeline=pipeline,
            data_prefix=data_prefix,
            modality=modality,
            test_mode=test_mode,
            ignore_index=ignore_index,
            scene_idxs=scene_idxs,
            file_client_args=file_client_args,
            **kwargs)