Added image loading in SUNRGB-D dataset

mmdet3d/datasets/sunrgbd_dataset.py

@@ -59,6 +59,55 @@ def __init__(self,
  box_type_3d=box_type_3d,
  filter_empty_gt=filter_empty_gt,
  test_mode=test_mode)
+ if self.modality is None:
+ self.modality = dict(
+ use_camera=True,
+ use_lidar=True,
+ )
+ assert self.modality['use_camera'] or self.modality['use_lidar']
+
+ def get_data_info(self, index):
+ """Get data info according to the given index.
+
+ Args:
+ index (int): Index of the sample data to get.
+
+ Returns:
+ dict: Data information that will be passed to the data \
+ preprocessing pipelines. It includes the following keys:
+
+ - sample_idx (str): Sample index.
+ - pts_filename (str, optional): Filename of point clouds.
+ - file_name (str, optional): Filename of point clouds.
+ - img_prefix (str | None, optional): Prefix of image files.
+ - img_info (dict, optional): Image info.
+ - calib (dict, optional): Camera calibration info.
+ - ann_info (dict): Annotation info.
+ """
+ info = self.data_infos[index]
+ sample_idx = info['point_cloud']['lidar_idx']
+ assert info['point_cloud']['lidar_idx'] == info['image']['image_idx']
+ input_dict = dict(sample_idx=sample_idx)
+
+ if self.modality['use_lidar']:
+ pts_filename = osp.join(self.data_root, info['pts_path'])
+ input_dict['pts_filename'] = pts_filename
+ input_dict['file_name'] = pts_filename
+
+ if self.modality['use_camera']:
+ img_filename = osp.join(self.data_root,
+ info['image']['image_path'])
+ input_dict['img_prefix'] = None
+ input_dict['img_info'] = dict(filename=img_filename)
+ calib = info['calib']
+ input_dict['calib'] = calib
+
+ if not self.test_mode:
+ annos = self.get_ann_info(index)
+ input_dict['ann_info'] = annos
+ if self.filter_empty_gt and len(annos['gt_bboxes_3d']) == 0:
+ return None
+ return input_dict
 
  def get_ann_info(self, index):
  """Get annotation info according to the given index.

mmdet3d/models/detectors/__init__.py

@@ -10,7 +10,15 @@
 from .voxelnet import VoxelNet
 
 __all__ = [
- 'Base3DDetector', 'VoxelNet', 'DynamicVoxelNet', 'MVXTwoStageDetector',
- 'DynamicMVXFasterRCNN', 'MVXFasterRCNN', 'PartA2', 'VoteNet', 'H3DNet',
- 'CenterPoint', 'SSD3DNet'
+ 'Base3DDetector',
+ 'VoxelNet',
+ 'DynamicVoxelNet',
+ 'MVXTwoStageDetector',
+ 'DynamicMVXFasterRCNN',
+ 'MVXFasterRCNN',
+ 'PartA2',
+ 'VoteNet',
+ 'H3DNet',
+ 'CenterPoint',
+ 'SSD3DNet',
 ]

mmdet3d/models/detectors/votenet.py

@@ -7,10 +7,7 @@
 
 @DETECTORS.register_module()
 class VoteNet(SingleStage3DDetector):
- """VoteNet model.
-
- https://arxiv.org/pdf/1904.09664.pdf
- """
+ r"""`VoteNet <https://arxiv.org/pdf/1904.09664.pdf>`_ for 3D detection."""
 
  def __init__(self,
  backbone,

tools/data_converter/sunrgbd_data_utils.py

@@ -155,8 +155,7 @@ def process_single_scene(sample_idx):
  osp.join(self.root_dir, 'points', f'{sample_idx:06d}.bin'))
 
  info['pts_path'] = osp.join('points', f'{sample_idx:06d}.bin')
- img_name = osp.join(self.image_dir, f'{sample_idx:06d}')
- img_path = osp.join(self.image_dir, img_name)
+ img_path = osp.join('image', f'{sample_idx:06d}.jpg')
  image_info = {
  'image_idx': sample_idx,
  'image_shape': self.get_image_shape(sample_idx),