Merge branch 'process_raw_data' into 'master'

Process raw data

See merge request open-mmlab/mmdet.3d!54

.gitignore

@@ -125,3 +125,5 @@ exps/
 # demo
 *.jpg
 *.png
+/data/scannet/scans/
+/data/sunrgbd/OFFICIAL_SUNRGBD/

.isort.cfg

@@ -3,6 +3,6 @@ line_length = 79
 multi_line_output = 0
 known_standard_library = setuptools
 known_first_party = mmdet,mmdet3d
-known_third_party = cv2,matplotlib,mmcv,numba,numpy,nuscenes,pycocotools,pyquaternion,pytest,scipy,seaborn,shapely,six,skimage,terminaltables,torch,torchvision
+known_third_party = cv2,load_scannet_data,matplotlib,mmcv,numba,numpy,nuscenes,plyfile,pycocotools,pyquaternion,pytest,scannet_utils,scipy,seaborn,shapely,six,skimage,sunrgbd_utils,terminaltables,torch,torchvision
 no_lines_before = STDLIB,LOCALFOLDER
 default_section = THIRDPARTY

data/scannet/README.md

+### Prepare ScanNet Data
+We follow the procedure in [votenet](https://github.com/facebookresearch/votenet/).
+
+1. Download ScanNet v2 data [HERE](https://github.com/ScanNet/ScanNet). Link or move the 'scans' folder to this level of directory.
+
+2. In this directory, extract point clouds and annotations by running `python batch_load_scannet_data.py`.
+
+3. Enter the project root directory, generate training data by running
+```bash
+python tools/create_data.py scannet --root-path ./data/scannet --out-dir ./data/scannet --extra-tag scannet
+```
+
+The overall process could be achieved through the following script
+```bash
+python batch_load_scannet_data.py
+cd ../..
+python tools/create_data.py scannet --root-path ./data/scannet --out-dir ./data/scannet --extra-tag scannet
+```
+
+The directory structure after pre-processing should be as below
+```
+scannet
+├── scannet_utils.py
+├── batch_load_scannet_data.py
+├── load_scannet_data.py
+├── scannet_utils.py
+├── README.md
+├── scans
+├── scannet_train_instance_data
+├── points
+├── instance_mask
+├── semantic_mask
+├── scannet_infos_train.pkl
+├── scannet_infos_val.pkl
+
+```

data/scannet/batch_load_scannet_data.py

+# Modified from
+# https://github.com/facebookresearch/votenet/blob/master/scannet/batch_load_scannet_data.py
+# Copyright (c) Facebook, Inc. and its affiliates.
+#
+# This source code is licensed under the MIT license found in the
+# LICENSE file in the root directory of this source tree.
+"""Batch mode in loading Scannet scenes with vertices and ground truth labels
+for semantic and instance segmentations
+
+Usage example: python ./batch_load_scannet_data.py
+"""
+
+import argparse
+import datetime
+import os
+import os.path as osp
+
+import numpy as np
+from load_scannet_data import export
+
+SCANNET_DIR = 'scans'
+DONOTCARE_CLASS_IDS = np.array([])
+OBJ_CLASS_IDS = np.array(
+    [3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 14, 16, 24, 28, 33, 34, 36, 39])
+
+
+def export_one_scan(scan_name, output_filename_prefix, max_num_point,
+                    label_map_file, scannet_dir):
+    mesh_file = osp.join(scannet_dir, scan_name, scan_name + '_vh_clean_2.ply')
+    agg_file = osp.join(scannet_dir, scan_name,
+                        scan_name + '.aggregation.json')
+    seg_file = osp.join(scannet_dir, scan_name,
+                        scan_name + '_vh_clean_2.0.010000.segs.json')
+    # includes axisAlignment info for the train set scans.
+    meta_file = osp.join(scannet_dir, scan_name, f'{scan_name}.txt')
+    mesh_vertices, semantic_labels, instance_labels, instance_bboxes, \
+        instance2semantic = export(mesh_file, agg_file, seg_file,
+                                   meta_file, label_map_file, None)
+
+    mask = np.logical_not(np.in1d(semantic_labels, DONOTCARE_CLASS_IDS))
+    mesh_vertices = mesh_vertices[mask, :]
+    semantic_labels = semantic_labels[mask]
+    instance_labels = instance_labels[mask]
+
+    num_instances = len(np.unique(instance_labels))
+    print(f'Num of instances: {num_instances}')
+
+    bbox_mask = np.in1d(instance_bboxes[:, -1], OBJ_CLASS_IDS)
+    instance_bboxes = instance_bboxes[bbox_mask, :]
+    print(f'Num of care instances: {instance_bboxes.shape[0]}')
+
+    N = mesh_vertices.shape[0]
+    if N > max_num_point:
+        choices = np.random.choice(N, max_num_point, replace=False)
+        mesh_vertices = mesh_vertices[choices, :]
+        semantic_labels = semantic_labels[choices]
+        instance_labels = instance_labels[choices]
+
+    np.save(f'{output_filename_prefix}_vert.npy', mesh_vertices)
+    np.save(f'{output_filename_prefix}_sem_label.npy', semantic_labels)
+    np.save(f'{output_filename_prefix}_ins_label.npy', instance_labels)
+    np.save(f'{output_filename_prefix}_bbox.npy', instance_bboxes)
+
+
+def batch_export(max_num_point, output_folder, train_scan_names_file,
+                 label_map_file, scannet_dir):
+    if not os.path.exists(output_folder):
+        print(f'Creating new data folder: {output_folder}')
+        os.mkdir(output_folder)
+
+    train_scan_names = [line.rstrip() for line in open(train_scan_names_file)]
+    for scan_name in train_scan_names:
+        print('-' * 20 + 'begin')
+        print(datetime.datetime.now())
+        print(scan_name)
+        output_filename_prefix = osp.join(output_folder, scan_name)
+        if osp.isfile(f'{output_filename_prefix}_vert.npy'):
+            print('File already exists. skipping.')
+            print('-' * 20 + 'done')
+            continue
+        try:
+            export_one_scan(scan_name, output_filename_prefix, max_num_point,
+                            label_map_file, scannet_dir)
+        except Exception:
+            print(f'Failed export scan: {scan_name}')
+        print('-' * 20 + 'done')
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        '--max_num_point',
+        default=50000,
+        help='The maximum number of the points.')
+    parser.add_argument(
+        '--output_folder',
+        default='./scannet_train_instance_data',
+        help='output folder of the result.')
+    parser.add_argument(
+        '--scannet_dir', default='scans', help='scannet data directory.')
+    parser.add_argument(
+        '--label_map_file',
+        default='meta_data/scannetv2-labels.combined.tsv',
+        help='The path of label map file.')
+    parser.add_argument(
+        '--train_scan_names_file',
+        default='meta_data/scannet_train.txt',
+        help='The path of the file that stores the scan names.')
+    args = parser.parse_args()
+    batch_export(args.max_num_point, args.output_folder,
+                 args.train_scan_names_file, args.label_map_file,
+                 args.scannet_dir)
+
+
+if __name__ == '__main__':
+    main()

data/scannet/load_scannet_data.py

+# Modified from
+# https://github.com/facebookresearch/votenet/blob/master/scannet/load_scannet_data.py
+# Copyright (c) Facebook, Inc. and its affiliates.
+#
+# This source code is licensed under the MIT license found in the
+# LICENSE file in the root directory of this source tree.
+"""Load Scannet scenes with vertices and ground truth labels
+for semantic and instance segmentations
+"""
+
+import argparse
+import inspect
+import json
+import os
+
+import numpy as np
+import scannet_utils
+
+currentdir = os.path.dirname(
+    os.path.abspath(inspect.getfile(inspect.currentframe())))
+
+
+def read_aggregation(filename):
+    assert os.path.isfile(filename)
+    object_id_to_segs = {}
+    label_to_segs = {}
+    with open(filename) as f:
+        data = json.load(f)
+        num_objects = len(data['segGroups'])
+        for i in range(num_objects):
+            object_id = data['segGroups'][i][
+                'objectId'] + 1  # instance ids should be 1-indexed
+            label = data['segGroups'][i]['label']
+            segs = data['segGroups'][i]['segments']
+            object_id_to_segs[object_id] = segs
+            if label in label_to_segs:
+                label_to_segs[label].extend(segs)
+            else:
+                label_to_segs[label] = segs
+    return object_id_to_segs, label_to_segs
+
+
+def read_segmentation(filename):
+    assert os.path.isfile(filename)
+    seg_to_verts = {}
+    with open(filename) as f:
+        data = json.load(f)
+        num_verts = len(data['segIndices'])
+        for i in range(num_verts):
+            seg_id = data['segIndices'][i]
+            if seg_id in seg_to_verts:
+                seg_to_verts[seg_id].append(i)
+            else:
+                seg_to_verts[seg_id] = [i]
+    return seg_to_verts, num_verts
+
+
+def export(mesh_file,
+           agg_file,
+           seg_file,
+           meta_file,
+           label_map_file,
+           output_file=None):
+    """Export original files to vert, ins_label, sem_label and bbox file.
+
+    Args:
+        mesh_file(str): Path of the mesh_file.
+        agg_file(str): Path of the agg_file.
+        seg_file(str): Path of the seg_file.
+        meta_file(str): Path of the meta_file.
+        label_map_file(str): Path of the label_map_file.
+        output_file(str): Path of the output folder.
+            Default: None.
+
+    It returns a tuple, which containts the the following things:
+        ndarray: Vertices of points data.
+        ndarray: Indexes of label.
+        ndarray: Indexes of instance.
+        ndarray: Instance bboxes.
+        dict: Map from object_id to label_id.
+    """
+
+    label_map = scannet_utils.read_label_mapping(
+        label_map_file, label_from='raw_category', label_to='nyu40id')
+    mesh_vertices = scannet_utils.read_mesh_vertices_rgb(mesh_file)
+
+    # Load scene axis alignment matrix
+    lines = open(meta_file).readlines()
+    for line in lines:
+        if 'axisAlignment' in line:
+            axis_align_matrix = [
+                float(x)
+                for x in line.rstrip().strip('axisAlignment = ').split(' ')
+            ]
+            break
+    axis_align_matrix = np.array(axis_align_matrix).reshape((4, 4))
+    pts = np.ones((mesh_vertices.shape[0], 4))
+    pts[:, 0:3] = mesh_vertices[:, 0:3]
+    pts = np.dot(pts, axis_align_matrix.transpose())  # Nx4
+    mesh_vertices[:, 0:3] = pts[:, 0:3]
+
+    # Load semantic and instance labels
+    object_id_to_segs, label_to_segs = read_aggregation(agg_file)
+    seg_to_verts, num_verts = read_segmentation(seg_file)
+    label_ids = np.zeros(shape=(num_verts), dtype=np.uint32)
+    object_id_to_label_id = {}
+    for label, segs in label_to_segs.items():
+        label_id = label_map[label]
+        for seg in segs:
+            verts = seg_to_verts[seg]
+            label_ids[verts] = label_id
+    instance_ids = np.zeros(
+        shape=(num_verts), dtype=np.uint32)  # 0: unannotated
+    num_instances = len(np.unique(list(object_id_to_segs.keys())))
+    for object_id, segs in object_id_to_segs.items():
+        for seg in segs:
+            verts = seg_to_verts[seg]
+            instance_ids[verts] = object_id
+            if object_id not in object_id_to_label_id:
+                object_id_to_label_id[object_id] = label_ids[verts][0]
+    instance_bboxes = np.zeros((num_instances, 7))
+    for obj_id in object_id_to_segs:
+        label_id = object_id_to_label_id[obj_id]
+        obj_pc = mesh_vertices[instance_ids == obj_id, 0:3]
+        if len(obj_pc) == 0:
+            continue
+        xmin = np.min(obj_pc[:, 0])
+        ymin = np.min(obj_pc[:, 1])
+        zmin = np.min(obj_pc[:, 2])
+        xmax = np.max(obj_pc[:, 0])
+        ymax = np.max(obj_pc[:, 1])
+        zmax = np.max(obj_pc[:, 2])
+        bbox = np.array([(xmin + xmax) / 2, (ymin + ymax) / 2,
+                         (zmin + zmax) / 2, xmax - xmin, ymax - ymin,
+                         zmax - zmin, label_id])
+        # NOTE: this assumes obj_id is in 1,2,3,.,,,.NUM_INSTANCES
+        instance_bboxes[obj_id - 1, :] = bbox
+
+    if output_file is not None:
+        np.save(output_file + '_vert.npy', mesh_vertices)
+        np.save(output_file + '_sem_label.npy', label_ids)
+        np.save(output_file + '_ins_label.npy', instance_ids)
+        np.save(output_file + '_bbox.npy', instance_bboxes)
+
+    return mesh_vertices, label_ids, instance_ids,\
+        instance_bboxes, object_id_to_label_id
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        '--scan_path',
+        required=True,
+        help='path to scannet scene (e.g., data/ScanNet/v2/scene0000_00')
+    parser.add_argument('--output_file', required=True, help='output file')
+    parser.add_argument(
+        '--label_map_file',
+        required=True,
+        help='path to scannetv2-labels.combined.tsv')
+    opt = parser.parse_args()
+
+    scan_name = os.path.split(opt.scan_path)[-1]
+    mesh_file = os.path.join(opt.scan_path, scan_name + '_vh_clean_2.ply')
+    agg_file = os.path.join(opt.scan_path, scan_name + '.aggregation.json')
+    seg_file = os.path.join(opt.scan_path,
+                            scan_name + '_vh_clean_2.0.010000.segs.json')
+    meta_file = os.path.join(
+        opt.scan_path, scan_name +
+        '.txt')  # includes axisAlignment info for the train set scans.
+    export(mesh_file, agg_file, seg_file, meta_file, opt.label_map_file,
+           opt.output_file)
+
+
+if __name__ == '__main__':
+    main()

data/scannet/meta_data/scannetv2_test.txt

+scene0707_00
+scene0708_00
+scene0709_00
+scene0710_00
+scene0711_00
+scene0712_00
+scene0713_00
+scene0714_00
+scene0715_00
+scene0716_00
+scene0717_00
+scene0718_00
+scene0719_00
+scene0720_00
+scene0721_00
+scene0722_00
+scene0723_00
+scene0724_00
+scene0725_00
+scene0726_00
+scene0727_00
+scene0728_00
+scene0729_00
+scene0730_00
+scene0731_00
+scene0732_00
+scene0733_00
+scene0734_00
+scene0735_00
+scene0736_00
+scene0737_00
+scene0738_00
+scene0739_00
+scene0740_00
+scene0741_00
+scene0742_00
+scene0743_00
+scene0744_00
+scene0745_00
+scene0746_00
+scene0747_00
+scene0748_00
+scene0749_00
+scene0750_00
+scene0751_00
+scene0752_00
+scene0753_00
+scene0754_00
+scene0755_00
+scene0756_00
+scene0757_00
+scene0758_00
+scene0759_00
+scene0760_00
+scene0761_00
+scene0762_00
+scene0763_00
+scene0764_00
+scene0765_00
+scene0766_00
+scene0767_00
+scene0768_00
+scene0769_00
+scene0770_00
+scene0771_00
+scene0772_00
+scene0773_00
+scene0774_00
+scene0775_00
+scene0776_00
+scene0777_00
+scene0778_00
+scene0779_00
+scene0780_00
+scene0781_00
+scene0782_00
+scene0783_00
+scene0784_00
+scene0785_00
+scene0786_00
+scene0787_00
+scene0788_00
+scene0789_00
+scene0790_00
+scene0791_00
+scene0792_00
+scene0793_00
+scene0794_00
+scene0795_00
+scene0796_00
+scene0797_00
+scene0798_00
+scene0799_00
+scene0800_00
+scene0801_00
+scene0802_00
+scene0803_00
+scene0804_00
+scene0805_00
+scene0806_00

data/scannet/meta_data/scannetv2_train.txt

+scene0191_00
+scene0191_01
+scene0191_02
+scene0119_00
+scene0230_00
+scene0528_00
+scene0528_01
+scene0705_00
+scene0705_01
+scene0705_02
+scene0415_00
+scene0415_01
+scene0415_02
+scene0007_00
+scene0141_00
+scene0141_01
+scene0141_02
+scene0515_00
+scene0515_01
+scene0515_02
+scene0447_00
+scene0447_01
+scene0447_02
+scene0531_00
+scene0503_00
+scene0285_00
+scene0069_00
+scene0584_00
+scene0584_01
+scene0584_02
+scene0581_00
+scene0581_01
+scene0581_02
+scene0620_00
+scene0620_01
+scene0263_00
+scene0263_01
+scene0481_00
+scene0481_01
+scene0020_00
+scene0020_01
+scene0291_00
+scene0291_01
+scene0291_02
+scene0469_00
+scene0469_01
+scene0469_02
+scene0659_00
+scene0659_01
+scene0024_00
+scene0024_01
+scene0024_02
+scene0564_00
+scene0117_00
+scene0027_00
+scene0027_01
+scene0027_02
+scene0028_00
+scene0330_00
+scene0418_00
+scene0418_01
+scene0418_02
+scene0233_00
+scene0233_01
+scene0673_00
+scene0673_01
+scene0673_02
+scene0673_03
+scene0673_04
+scene0673_05
+scene0585_00
+scene0585_01
+scene0362_00
+scene0362_01
+scene0362_02
+scene0362_03
+scene0035_00
+scene0035_01
+scene0358_00
+scene0358_01
+scene0358_02
+scene0037_00
+scene0194_00
+scene0321_00
+scene0293_00
+scene0293_01
+scene0623_00
+scene0623_01
+scene0592_00
+scene0592_01
+scene0569_00
+scene0569_01
+scene0413_00
+scene0313_00
+scene0313_01
+scene0313_02
+scene0480_00
+scene0480_01
+scene0401_00
+scene0517_00
+scene0517_01
+scene0517_02
+scene0032_00
+scene0032_01
+scene0613_00
+scene0613_01
+scene0613_02
+scene0306_00
+scene0306_01
+scene0052_00
+scene0052_01
+scene0052_02
+scene0053_00
+scene0444_00
+scene0444_01
+scene0055_00
+scene0055_01
+scene0055_02
+scene0560_00
+scene0589_00
+scene0589_01
+scene0589_02
+scene0610_00
+scene0610_01
+scene0610_02
+scene0364_00
+scene0364_01
+scene0383_00
+scene0383_01
+scene0383_02
+scene0006_00
+scene0006_01
+scene0006_02
+scene0275_00
+scene0451_00
+scene0451_01
+scene0451_02
+scene0451_03
+scene0451_04
+scene0451_05
+scene0135_00
+scene0065_00
+scene0065_01
+scene0065_02
+scene0104_00
+scene0674_00
+scene0674_01
+scene0448_00
+scene0448_01
+scene0448_02
+scene0502_00
+scene0502_01
+scene0502_02
+scene0440_00
+scene0440_01
+scene0440_02
+scene0071_00
+scene0072_00
+scene0072_01
+scene0072_02
+scene0509_00
+scene0509_01
+scene0509_02
+scene0649_00
+scene0649_01
+scene0602_00
+scene0694_00
+scene0694_01
+scene0101_00
+scene0101_01
+scene0101_02
+scene0101_03
+scene0101_04
+scene0101_05
+scene0218_00
+scene0218_01
+scene0579_00
+scene0579_01
+scene0579_02
+scene0039_00
+scene0039_01
+scene0493_00
+scene0493_01
+scene0242_00
+scene0242_01
+scene0242_02
+scene0083_00
+scene0083_01
+scene0127_00
+scene0127_01
+scene0662_00
+scene0662_01
+scene0662_02
+scene0018_00
+scene0087_00
+scene0087_01
+scene0087_02
+scene0332_00
+scene0332_01
+scene0332_02
+scene0628_00
+scene0628_01
+scene0628_02
+scene0134_00
+scene0134_01
+scene0134_02
+scene0238_00
+scene0238_01
+scene0092_00
+scene0092_01
+scene0092_02
+scene0092_03
+scene0092_04
+scene0022_00
+scene0022_01
+scene0467_00
+scene0392_00
+scene0392_01
+scene0392_02
+scene0424_00
+scene0424_01
+scene0424_02
+scene0646_00
+scene0646_01
+scene0646_02
+scene0098_00
+scene0098_01
+scene0044_00
+scene0044_01
+scene0044_02
+scene0510_00
+scene0510_01
+scene0510_02
+scene0571_00
+scene0571_01
+scene0166_00
+scene0166_01
+scene0166_02
+scene0563_00
+scene0172_00
+scene0172_01
+scene0388_00
+scene0388_01
+scene0215_00
+scene0215_01
+scene0252_00
+scene0287_00
+scene0668_00
+scene0572_00
+scene0572_01
+scene0572_02
+scene0026_00
+scene0224_00
+scene0113_00
+scene0113_01
+scene0551_00
+scene0381_00
+scene0381_01
+scene0381_02
+scene0371_00
+scene0371_01
+scene0460_00
+scene0118_00
+scene0118_01
+scene0118_02
+scene0417_00
+scene0008_00
+scene0634_00
+scene0521_00
+scene0123_00
+scene0123_01
+scene0123_02
+scene0045_00
+scene0045_01
+scene0511_00
+scene0511_01
+scene0114_00
+scene0114_01
+scene0114_02
+scene0070_00
+scene0029_00
+scene0029_01
+scene0029_02
+scene0129_00
+scene0103_00
+scene0103_01
+scene0002_00
+scene0002_01
+scene0132_00
+scene0132_01
+scene0132_02
+scene0124_00
+scene0124_01
+scene0143_00
+scene0143_01
+scene0143_02
+scene0604_00
+scene0604_01
+scene0604_02
+scene0507_00
+scene0105_00
+scene0105_01
+scene0105_02
+scene0428_00
+scene0428_01
+scene0311_00
+scene0140_00
+scene0140_01
+scene0182_00
+scene0182_01
+scene0182_02
+scene0142_00
+scene0142_01
+scene0399_00
+scene0399_01
+scene0012_00
+scene0012_01
+scene0012_02
+scene0060_00
+scene0060_01
+scene0370_00
+scene0370_01
+scene0370_02
+scene0310_00
+scene0310_01
+scene0310_02
+scene0661_00
+scene0650_00
+scene0152_00
+scene0152_01
+scene0152_02
+scene0158_00
+scene0158_01
+scene0158_02
+scene0482_00
+scene0482_01
+scene0600_00
+scene0600_01
+scene0600_02
+scene0393_00
+scene0393_01
+scene0393_02
+scene0562_00
+scene0174_00
+scene0174_01
+scene0157_00
+scene0157_01
+scene0161_00
+scene0161_01
+scene0161_02
+scene0159_00
+scene0254_00
+scene0254_01
+scene0115_00
+scene0115_01
+scene0115_02
+scene0162_00
+scene0163_00
+scene0163_01
+scene0523_00
+scene0523_01
+scene0523_02
+scene0459_00
+scene0459_01
+scene0175_00
+scene0085_00
+scene0085_01
+scene0279_00
+scene0279_01
+scene0279_02
+scene0201_00
+scene0201_01
+scene0201_02
+scene0283_00
+scene0456_00
+scene0456_01
+scene0429_00
+scene0043_00
+scene0043_01
+scene0419_00
+scene0419_01
+scene0419_02
+scene0368_00
+scene0368_01
+scene0348_00
+scene0348_01
+scene0348_02
+scene0442_00
+scene0178_00
+scene0380_00
+scene0380_01
+scene0380_02
+scene0165_00
+scene0165_01
+scene0165_02
+scene0181_00
+scene0181_01
+scene0181_02
+scene0181_03
+scene0333_00
+scene0614_00
+scene0614_01
+scene0614_02
+scene0404_00
+scene0404_01
+scene0404_02
+scene0185_00
+scene0126_00
+scene0126_01
+scene0126_02
+scene0519_00
+scene0236_00
+scene0236_01
+scene0189_00
+scene0075_00
+scene0267_00
+scene0192_00
+scene0192_01
+scene0192_02
+scene0281_00
+scene0420_00
+scene0420_01
+scene0420_02
+scene0195_00
+scene0195_01
+scene0195_02
+scene0597_00
+scene0597_01
+scene0597_02
+scene0041_00
+scene0041_01
+scene0111_00
+scene0111_01
+scene0111_02
+scene0666_00
+scene0666_01
+scene0666_02
+scene0200_00
+scene0200_01
+scene0200_02
+scene0536_00
+scene0536_01
+scene0536_02
+scene0390_00
+scene0280_00
+scene0280_01
+scene0280_02
+scene0344_00
+scene0344_01
+scene0205_00
+scene0205_01
+scene0205_02
+scene0484_00
+scene0484_01
+scene0009_00
+scene0009_01
+scene0009_02
+scene0302_00
+scene0302_01
+scene0209_00
+scene0209_01
+scene0209_02
+scene0210_00
+scene0210_01
+scene0395_00
+scene0395_01
+scene0395_02
+scene0683_00
+scene0601_00
+scene0601_01
+scene0214_00
+scene0214_01
+scene0214_02
+scene0477_00
+scene0477_01
+scene0439_00
+scene0439_01
+scene0468_00
+scene0468_01
+scene0468_02
+scene0546_00
+scene0466_00
+scene0466_01
+scene0220_00
+scene0220_01
+scene0220_02
+scene0122_00
+scene0122_01
+scene0130_00
+scene0110_00
+scene0110_01
+scene0110_02
+scene0327_00
+scene0156_00
+scene0266_00
+scene0266_01
+scene0001_00
+scene0001_01
+scene0228_00
+scene0199_00
+scene0219_00
+scene0464_00
+scene0232_00
+scene0232_01
+scene0232_02
+scene0299_00
+scene0299_01
+scene0530_00
+scene0363_00
+scene0453_00
+scene0453_01
+scene0570_00
+scene0570_01
+scene0570_02
+scene0183_00
+scene0239_00
+scene0239_01
+scene0239_02
+scene0373_00
+scene0373_01
+scene0241_00
+scene0241_01
+scene0241_02
+scene0188_00
+scene0622_00
+scene0622_01
+scene0244_00
+scene0244_01
+scene0691_00
+scene0691_01
+scene0206_00
+scene0206_01
+scene0206_02
+scene0247_00
+scene0247_01
+scene0061_00
+scene0061_01
+scene0082_00
+scene0250_00
+scene0250_01
+scene0250_02
+scene0501_00
+scene0501_01
+scene0501_02
+scene0320_00
+scene0320_01
+scene0320_02
+scene0320_03
+scene0631_00
+scene0631_01
+scene0631_02
+scene0255_00
+scene0255_01
+scene0255_02
+scene0047_00
+scene0265_00
+scene0265_01
+scene0265_02
+scene0004_00
+scene0336_00
+scene0336_01
+scene0058_00
+scene0058_01
+scene0260_00
+scene0260_01
+scene0260_02
+scene0243_00
+scene0603_00
+scene0603_01
+scene0093_00
+scene0093_01
+scene0093_02
+scene0109_00
+scene0109_01
+scene0434_00
+scene0434_01
+scene0434_02
+scene0290_00
+scene0627_00
+scene0627_01
+scene0470_00
+scene0470_01
+scene0137_00
+scene0137_01
+scene0137_02
+scene0270_00
+scene0270_01
+scene0270_02
+scene0271_00
+scene0271_01
+scene0504_00
+scene0274_00
+scene0274_01
+scene0274_02
+scene0036_00
+scene0036_01
+scene0276_00
+scene0276_01
+scene0272_00
+scene0272_01
+scene0499_00
+scene0698_00
+scene0698_01
+scene0051_00
+scene0051_01
+scene0051_02
+scene0051_03
+scene0108_00
+scene0245_00
+scene0369_00
+scene0369_01
+scene0369_02
+scene0284_00
+scene0289_00
+scene0289_01
+scene0286_00
+scene0286_01
+scene0286_02
+scene0286_03
+scene0031_00
+scene0031_01
+scene0031_02
+scene0545_00
+scene0545_01
+scene0545_02
+scene0557_00
+scene0557_01
+scene0557_02
+scene0533_00
+scene0533_01
+scene0116_00
+scene0116_01
+scene0116_02
+scene0611_00
+scene0611_01
+scene0688_00
+scene0294_00
+scene0294_01
+scene0294_02
+scene0295_00
+scene0295_01
+scene0296_00
+scene0296_01
+scene0596_00
+scene0596_01
+scene0596_02
+scene0532_00
+scene0532_01
+scene0637_00
+scene0638_00
+scene0121_00
+scene0121_01
+scene0121_02
+scene0040_00
+scene0040_01
+scene0197_00
+scene0197_01
+scene0197_02
+scene0410_00
+scene0410_01
+scene0305_00
+scene0305_01
+scene0615_00
+scene0615_01
+scene0703_00
+scene0703_01
+scene0555_00
+scene0297_00
+scene0297_01
+scene0297_02
+scene0582_00
+scene0582_01
+scene0582_02
+scene0023_00
+scene0094_00
+scene0013_00
+scene0013_01
+scene0013_02
+scene0136_00
+scene0136_01
+scene0136_02
+scene0407_00
+scene0407_01
+scene0062_00
+scene0062_01
+scene0062_02
+scene0386_00
+scene0318_00
+scene0554_00
+scene0554_01
+scene0497_00
+scene0213_00
+scene0258_00
+scene0323_00
+scene0323_01
+scene0324_00
+scene0324_01
+scene0016_00
+scene0016_01
+scene0016_02
+scene0681_00
+scene0398_00
+scene0398_01
+scene0227_00
+scene0090_00
+scene0066_00
+scene0262_00
+scene0262_01
+scene0155_00
+scene0155_01
+scene0155_02
+scene0352_00
+scene0352_01
+scene0352_02
+scene0038_00
+scene0038_01
+scene0038_02
+scene0335_00
+scene0335_01
+scene0335_02
+scene0261_00
+scene0261_01
+scene0261_02
+scene0261_03
+scene0640_00
+scene0640_01
+scene0640_02
+scene0080_00
+scene0080_01
+scene0080_02
+scene0403_00
+scene0403_01
+scene0282_00
+scene0282_01
+scene0282_02
+scene0682_00
+scene0173_00
+scene0173_01
+scene0173_02
+scene0522_00
+scene0687_00
+scene0345_00
+scene0345_01
+scene0612_00
+scene0612_01
+scene0411_00
+scene0411_01
+scene0411_02
+scene0625_00
+scene0625_01
+scene0211_00
+scene0211_01
+scene0211_02
+scene0211_03
+scene0676_00
+scene0676_01
+scene0179_00
+scene0498_00
+scene0498_01
+scene0498_02
+scene0547_00
+scene0547_01
+scene0547_02
+scene0269_00
+scene0269_01
+scene0269_02
+scene0366_00
+scene0680_00
+scene0680_01
+scene0588_00
+scene0588_01
+scene0588_02
+scene0588_03
+scene0346_00
+scene0346_01
+scene0359_00
+scene0359_01
+scene0014_00
+scene0120_00
+scene0120_01
+scene0212_00
+scene0212_01
+scene0212_02
+scene0176_00
+scene0049_00
+scene0259_00
+scene0259_01
+scene0586_00
+scene0586_01
+scene0586_02
+scene0309_00
+scene0309_01
+scene0125_00
+scene0455_00
+scene0177_00
+scene0177_01
+scene0177_02
+scene0326_00
+scene0372_00
+scene0171_00
+scene0171_01
+scene0374_00
+scene0654_00
+scene0654_01
+scene0445_00
+scene0445_01
+scene0475_00
+scene0475_01
+scene0475_02
+scene0349_00
+scene0349_01
+scene0234_00
+scene0669_00
+scene0669_01
+scene0375_00
+scene0375_01
+scene0375_02
+scene0387_00
+scene0387_01
+scene0387_02
+scene0312_00
+scene0312_01
+scene0312_02
+scene0384_00
+scene0385_00
+scene0385_01
+scene0385_02
+scene0000_00
+scene0000_01
+scene0000_02
+scene0376_00
+scene0376_01
+scene0376_02
+scene0301_00
+scene0301_01
+scene0301_02
+scene0322_00
+scene0542_00
+scene0079_00
+scene0079_01
+scene0099_00
+scene0099_01
+scene0476_00
+scene0476_01
+scene0476_02
+scene0394_00
+scene0394_01
+scene0147_00
+scene0147_01
+scene0067_00
+scene0067_01
+scene0067_02
+scene0397_00
+scene0397_01
+scene0337_00
+scene0337_01
+scene0337_02
+scene0431_00
+scene0223_00
+scene0223_01
+scene0223_02
+scene0010_00
+scene0010_01
+scene0402_00
+scene0268_00
+scene0268_01
+scene0268_02
+scene0679_00
+scene0679_01
+scene0405_00
+scene0128_00
+scene0408_00
+scene0408_01
+scene0190_00
+scene0107_00
+scene0076_00
+scene0167_00
+scene0361_00
+scene0361_01
+scene0361_02
+scene0216_00
+scene0202_00
+scene0303_00
+scene0303_01
+scene0303_02
+scene0446_00
+scene0446_01
+scene0089_00
+scene0089_01
+scene0089_02
+scene0360_00
+scene0150_00
+scene0150_01
+scene0150_02
+scene0421_00
+scene0421_01
+scene0421_02
+scene0454_00
+scene0626_00
+scene0626_01
+scene0626_02
+scene0186_00
+scene0186_01
+scene0538_00
+scene0479_00
+scene0479_01
+scene0479_02
+scene0656_00
+scene0656_01
+scene0656_02
+scene0656_03
+scene0525_00
+scene0525_01
+scene0525_02
+scene0308_00
+scene0396_00
+scene0396_01
+scene0396_02
+scene0624_00
+scene0292_00
+scene0292_01
+scene0632_00
+scene0253_00
+scene0021_00
+scene0325_00
+scene0325_01
+scene0437_00
+scene0437_01
+scene0438_00
+scene0590_00
+scene0590_01
+scene0400_00
+scene0400_01
+scene0541_00
+scene0541_01
+scene0541_02
+scene0677_00
+scene0677_01
+scene0677_02
+scene0443_00
+scene0315_00
+scene0288_00
+scene0288_01
+scene0288_02
+scene0422_00
+scene0672_00
+scene0672_01
+scene0184_00
+scene0449_00
+scene0449_01
+scene0449_02
+scene0048_00
+scene0048_01
+scene0138_00
+scene0452_00
+scene0452_01
+scene0452_02
+scene0667_00
+scene0667_01
+scene0667_02
+scene0463_00
+scene0463_01
+scene0078_00
+scene0078_01
+scene0078_02
+scene0636_00
+scene0457_00
+scene0457_01
+scene0457_02
+scene0465_00
+scene0465_01
+scene0577_00
+scene0151_00
+scene0151_01
+scene0339_00
+scene0573_00
+scene0573_01
+scene0154_00
+scene0096_00
+scene0096_01
+scene0096_02
+scene0235_00
+scene0168_00
+scene0168_01
+scene0168_02
+scene0594_00
+scene0587_00
+scene0587_01
+scene0587_02
+scene0587_03
+scene0229_00
+scene0229_01
+scene0229_02
+scene0512_00
+scene0106_00
+scene0106_01
+scene0106_02
+scene0472_00
+scene0472_01
+scene0472_02
+scene0489_00
+scene0489_01
+scene0489_02
+scene0425_00
+scene0425_01
+scene0641_00
+scene0526_00
+scene0526_01
+scene0317_00
+scene0317_01
+scene0544_00
+scene0017_00
+scene0017_01
+scene0017_02
+scene0042_00
+scene0042_01
+scene0042_02
+scene0576_00
+scene0576_01
+scene0576_02
+scene0347_00
+scene0347_01
+scene0347_02
+scene0436_00
+scene0226_00
+scene0226_01
+scene0485_00
+scene0486_00
+scene0487_00
+scene0487_01
+scene0619_00
+scene0097_00
+scene0367_00
+scene0367_01
+scene0491_00
+scene0492_00
+scene0492_01
+scene0005_00
+scene0005_01
+scene0543_00
+scene0543_01
+scene0543_02
+scene0657_00
+scene0341_00
+scene0341_01
+scene0534_00
+scene0534_01
+scene0319_00
+scene0273_00
+scene0273_01
+scene0225_00
+scene0198_00
+scene0003_00
+scene0003_01
+scene0003_02
+scene0409_00
+scene0409_01
+scene0331_00
+scene0331_01
+scene0505_00
+scene0505_01
+scene0505_02
+scene0505_03
+scene0505_04
+scene0506_00
+scene0057_00
+scene0057_01
+scene0074_00
+scene0074_01
+scene0074_02
+scene0091_00
+scene0112_00
+scene0112_01
+scene0112_02
+scene0240_00
+scene0102_00
+scene0102_01
+scene0513_00
+scene0514_00
+scene0514_01
+scene0537_00
+scene0516_00
+scene0516_01
+scene0495_00
+scene0617_00
+scene0133_00
+scene0520_00
+scene0520_01
+scene0635_00
+scene0635_01
+scene0054_00
+scene0473_00
+scene0473_01
+scene0524_00
+scene0524_01
+scene0379_00
+scene0471_00
+scene0471_01
+scene0471_02
+scene0566_00
+scene0248_00
+scene0248_01
+scene0248_02
+scene0529_00
+scene0529_01
+scene0529_02
+scene0391_00
+scene0264_00
+scene0264_01
+scene0264_02
+scene0675_00
+scene0675_01
+scene0350_00
+scene0350_01
+scene0350_02
+scene0450_00
+scene0068_00
+scene0068_01
+scene0237_00
+scene0237_01
+scene0365_00
+scene0365_01
+scene0365_02
+scene0605_00
+scene0605_01
+scene0539_00
+scene0539_01
+scene0539_02
+scene0540_00
+scene0540_01
+scene0540_02
+scene0170_00
+scene0170_01
+scene0170_02
+scene0433_00
+scene0340_00
+scene0340_01
+scene0340_02
+scene0160_00
+scene0160_01
+scene0160_02
+scene0160_03
+scene0160_04
+scene0059_00
+scene0059_01
+scene0059_02
+scene0056_00
+scene0056_01
+scene0478_00
+scene0478_01
+scene0548_00
+scene0548_01
+scene0548_02
+scene0204_00
+scene0204_01
+scene0204_02
+scene0033_00
+scene0145_00
+scene0483_00
+scene0508_00
+scene0508_01
+scene0508_02
+scene0180_00
+scene0148_00
+scene0556_00
+scene0556_01
+scene0416_00
+scene0416_01
+scene0416_02
+scene0416_03
+scene0416_04
+scene0073_00
+scene0073_01
+scene0073_02
+scene0073_03
+scene0034_00
+scene0034_01
+scene0034_02
+scene0639_00
+scene0561_00
+scene0561_01
+scene0298_00
+scene0692_00
+scene0692_01
+scene0692_02
+scene0692_03
+scene0692_04
+scene0642_00
+scene0642_01
+scene0642_02
+scene0642_03
+scene0630_00
+scene0630_01
+scene0630_02
+scene0630_03
+scene0630_04
+scene0630_05
+scene0630_06
+scene0706_00
+scene0567_00
+scene0567_01

data/scannet/meta_data/scannetv2_val.txt

+scene0568_00
+scene0568_01
+scene0568_02
+scene0304_00
+scene0488_00
+scene0488_01
+scene0412_00
+scene0412_01
+scene0217_00
+scene0019_00
+scene0019_01
+scene0414_00
+scene0575_00
+scene0575_01
+scene0575_02
+scene0426_00
+scene0426_01
+scene0426_02
+scene0426_03
+scene0549_00
+scene0549_01
+scene0578_00
+scene0578_01
+scene0578_02
+scene0665_00
+scene0665_01
+scene0050_00
+scene0050_01
+scene0050_02
+scene0257_00
+scene0025_00
+scene0025_01
+scene0025_02
+scene0583_00
+scene0583_01
+scene0583_02
+scene0701_00
+scene0701_01
+scene0701_02
+scene0580_00
+scene0580_01
+scene0565_00
+scene0169_00
+scene0169_01
+scene0655_00
+scene0655_01
+scene0655_02
+scene0063_00
+scene0221_00
+scene0221_01
+scene0591_00
+scene0591_01
+scene0591_02
+scene0678_00
+scene0678_01
+scene0678_02
+scene0462_00
+scene0427_00
+scene0595_00
+scene0193_00
+scene0193_01
+scene0164_00
+scene0164_01
+scene0164_02
+scene0164_03
+scene0598_00
+scene0598_01
+scene0598_02
+scene0599_00
+scene0599_01
+scene0599_02
+scene0328_00
+scene0300_00
+scene0300_01
+scene0354_00
+scene0458_00
+scene0458_01
+scene0423_00
+scene0423_01
+scene0423_02
+scene0307_00
+scene0307_01
+scene0307_02
+scene0606_00
+scene0606_01
+scene0606_02
+scene0432_00
+scene0432_01
+scene0608_00
+scene0608_01
+scene0608_02
+scene0651_00
+scene0651_01
+scene0651_02
+scene0430_00
+scene0430_01
+scene0689_00
+scene0357_00
+scene0357_01
+scene0574_00
+scene0574_01
+scene0574_02
+scene0329_00
+scene0329_01
+scene0329_02
+scene0153_00
+scene0153_01
+scene0616_00
+scene0616_01
+scene0671_00
+scene0671_01
+scene0618_00
+scene0382_00
+scene0382_01
+scene0490_00
+scene0621_00
+scene0607_00
+scene0607_01
+scene0149_00
+scene0695_00
+scene0695_01
+scene0695_02
+scene0695_03
+scene0389_00
+scene0377_00
+scene0377_01
+scene0377_02
+scene0342_00
+scene0139_00
+scene0629_00
+scene0629_01
+scene0629_02
+scene0496_00
+scene0633_00
+scene0633_01
+scene0518_00
+scene0652_00
+scene0406_00
+scene0406_01
+scene0406_02
+scene0144_00
+scene0144_01
+scene0494_00
+scene0278_00
+scene0278_01
+scene0316_00
+scene0609_00
+scene0609_01
+scene0609_02
+scene0609_03
+scene0084_00
+scene0084_01
+scene0084_02
+scene0696_00
+scene0696_01
+scene0696_02
+scene0351_00
+scene0351_01
+scene0643_00
+scene0644_00
+scene0645_00
+scene0645_01
+scene0645_02
+scene0081_00
+scene0081_01
+scene0081_02
+scene0647_00
+scene0647_01
+scene0535_00
+scene0353_00
+scene0353_01
+scene0353_02
+scene0559_00
+scene0559_01
+scene0559_02
+scene0593_00
+scene0593_01
+scene0246_00
+scene0653_00
+scene0653_01
+scene0064_00
+scene0064_01
+scene0356_00
+scene0356_01
+scene0356_02
+scene0030_00
+scene0030_01
+scene0030_02
+scene0222_00
+scene0222_01
+scene0338_00
+scene0338_01
+scene0338_02
+scene0378_00
+scene0378_01
+scene0378_02
+scene0660_00
+scene0553_00
+scene0553_01
+scene0553_02
+scene0527_00
+scene0663_00
+scene0663_01
+scene0663_02
+scene0664_00
+scene0664_01
+scene0664_02
+scene0334_00
+scene0334_01
+scene0334_02
+scene0046_00
+scene0046_01
+scene0046_02
+scene0203_00
+scene0203_01
+scene0203_02
+scene0088_00
+scene0088_01
+scene0088_02
+scene0088_03
+scene0086_00
+scene0086_01
+scene0086_02
+scene0670_00
+scene0670_01
+scene0256_00
+scene0256_01
+scene0256_02
+scene0249_00
+scene0441_00
+scene0658_00
+scene0704_00
+scene0704_01
+scene0187_00
+scene0187_01
+scene0131_00
+scene0131_01
+scene0131_02
+scene0207_00
+scene0207_01
+scene0207_02
+scene0461_00
+scene0011_00
+scene0011_01
+scene0343_00
+scene0251_00
+scene0077_00
+scene0077_01
+scene0684_00
+scene0684_01
+scene0550_00
+scene0686_00
+scene0686_01
+scene0686_02
+scene0208_00
+scene0500_00
+scene0500_01
+scene0552_00
+scene0552_01
+scene0648_00
+scene0648_01
+scene0435_00
+scene0435_01
+scene0435_02
+scene0435_03
+scene0690_00
+scene0690_01
+scene0693_00
+scene0693_01
+scene0693_02
+scene0700_00
+scene0700_01
+scene0700_02
+scene0699_00
+scene0231_00
+scene0231_01
+scene0231_02
+scene0697_00
+scene0697_01
+scene0697_02
+scene0697_03
+scene0474_00
+scene0474_01
+scene0474_02
+scene0474_03
+scene0474_04
+scene0474_05
+scene0355_00
+scene0355_01
+scene0146_00
+scene0146_01
+scene0146_02
+scene0196_00
+scene0702_00
+scene0702_01
+scene0702_02
+scene0314_00
+scene0277_00
+scene0277_01
+scene0277_02
+scene0095_00
+scene0095_01
+scene0015_00
+scene0100_00
+scene0100_01
+scene0100_02
+scene0558_00
+scene0558_01
+scene0558_02
+scene0685_00
+scene0685_01
+scene0685_02

data/scannet/scannet_utils.py

+# Modified from
+# https://github.com/facebookresearch/votenet/blob/master/scannet/scannet_utils.py
+# Copyright (c) Facebook, Inc. and its affiliates.
+#
+# This source code is licensed under the MIT license found in the
+# LICENSE file in the root directory of this source tree.
+"""Ref: https://github.com/ScanNet/ScanNet/blob/master/BenchmarkScripts
+"""
+
+import csv
+import os
+
+import numpy as np
+from plyfile import PlyData
+
+
+def represents_int(s):
+    """Judge whether string s represents an int.
+
+    Args:
+        s(str): The input string to be judged.
+
+    Returns:
+        bool: Whether s represents int or not.
+    """
+    try:
+        int(s)
+        return True
+    except ValueError:
+        return False
+
+
+def read_label_mapping(filename,
+                       label_from='raw_category',
+                       label_to='nyu40id'):
+    assert os.path.isfile(filename)
+    mapping = dict()
+    with open(filename) as csvfile:
+        reader = csv.DictReader(csvfile, delimiter='\t')
+        for row in reader:
+            mapping[row[label_from]] = int(row[label_to])
+    if represents_int(list(mapping.keys())[0]):
+        mapping = {int(k): v for k, v in mapping.items()}
+    return mapping
+
+
+def read_mesh_vertices(filename):
+    """Read XYZ for each vertex.
+
+    Args:
+        filename(str): The name of the mesh vertices file.
+
+    Returns:
+        ndarray: Vertices.
+    """
+    assert os.path.isfile(filename)
+    with open(filename, 'rb') as f:
+        plydata = PlyData.read(f)
+        num_verts = plydata['vertex'].count
+        vertices = np.zeros(shape=[num_verts, 3], dtype=np.float32)
+        vertices[:, 0] = plydata['vertex'].data['x']
+        vertices[:, 1] = plydata['vertex'].data['y']
+        vertices[:, 2] = plydata['vertex'].data['z']
+    return vertices
+
+
+def read_mesh_vertices_rgb(filename):
+    """Read XYZ and RGB for each vertex.
+
+    Args:
+        filename(str): The name of the mesh vertices file.
+
+    Returns:
+        Vertices. Note that RGB values are in 0-255.
+    """
+    assert os.path.isfile(filename)
+    with open(filename, 'rb') as f:
+        plydata = PlyData.read(f)
+        num_verts = plydata['vertex'].count
+        vertices = np.zeros(shape=[num_verts, 6], dtype=np.float32)
+        vertices[:, 0] = plydata['vertex'].data['x']
+        vertices[:, 1] = plydata['vertex'].data['y']
+        vertices[:, 2] = plydata['vertex'].data['z']
+        vertices[:, 3] = plydata['vertex'].data['red']
+        vertices[:, 4] = plydata['vertex'].data['green']
+        vertices[:, 5] = plydata['vertex'].data['blue']
+    return vertices

data/sunrgbd/README.md

+### Prepare SUN RGB-D Data
+We follow the procedure in [votenet](https://github.com/facebookresearch/votenet/).
+
+1. Download SUNRGBD v2 data [HERE](http://rgbd.cs.princeton.edu/data/). Then, move SUNRGBD.zip, SUNRGBDMeta2DBB_v2.mat, SUNRGBDMeta3DBB_v2.mat and SUNRGBDtoolbox.zip to the OFFICIAL_SUNRGBD folder, unzip the zip files.
+
+2. Enter the `matlab` folder, Extract point clouds and annotations by running `extract_split.m`, `extract_rgbd_data_v2.m` and `extract_rgbd_data_v1.m`.
+
+3. Back to this directory, prepare data by running `python sunrgbd_data.py --gen_v1_data`.
+
+4. Enter the project root directory, Generate training data by running
+```bash
+python tools/create_data.py sunrgbd --root-path ./data/sunrgbd --out-dir ./data/sunrgbd --extra-tag sunrgbd
+```
+
+The overall process could be achieved through the following script
+```bash
+cd matlab
+matlab -nosplash -nodesktop -r 'extract_split;quit;'
+matlab -nosplash -nodesktop -r 'extract_rgbd_data_v2;quit;'
+matlab -nosplash -nodesktop -r 'extract_rgbd_data_v1;quit;'
+cd ..
+python sunrgbd_data.py --gen_v1_data
+cd ..
+python tools/create_data.py sunrgbd --root-path ./data/sunrgbd --out-dir ./data/sunrgbd --extra-tag sunrgbd
+```
+
+NOTE: SUNRGBDtoolbox.zip should have MD5 hash `18d22e1761d36352f37232cba102f91f` (you can check the hash with `md5 SUNRGBDtoolbox.zip` on Mac OS or `md5sum SUNRGBDtoolbox.zip` on Linux)
+
+The directory structure after pre-processing should be as below
+```
+sunrgbd
+├── sunrgbd_utils.py
+├── sunrgbd_data.py
+├── README.md
+├── matlab
+│   ├── extract_rgbd_data_v1.m
+│   ├── extract_rgbd_data_v2.m
+│   ├── extract_split.m
+├── OFFICIAL_SUNRGBD
+│   ├── SUNRGBD
+│   ├── SUNRGBDMeta2DBB_v2.mat
+│   ├── SUNRGBDMeta3DBB_v2.mat
+│   ├── SUNRGBDtoolbox
+├── sunrgbd_trainval
+│   ├── calib
+│   ├── image
+│   ├── label_v1
+│   ├── train_data_idx.txt
+│   ├── depth
+│   ├── label
+│   ├── seg_label
+│   ├── val_data_idx.txt
+├── sunrgbd_pc_bbox_votes_50k_v1_train
+├── sunrgbd_pc_bbox_votes_50k_v1_val
+├── points
+├── sunrgbd_infos_train.pkl
+├── sunrgbd_infos_val.pkl
+
+```

data/sunrgbd/matlab/extract_rgbd_data_v1.m

+% Copyright (c) Facebook, Inc. and its affiliates.
+%
+% This source code is licensed under the MIT license found in the
+% LICENSE file in the root directory of this source tree.
+
+%% Dump SUNRGBD data to our format
+% for each sample, we have RGB image, 2d boxes.
+% point cloud (in camera coordinate), calibration and 3d boxes.
+%
+% Extract using V1 labels.
+%
+% Author: Charles R. Qi
+%
+clear; close all; clc;
+addpath(genpath('.'))
+addpath('../OFFICIAL_SUNRGBD/SUNRGBDtoolbox')
+%% V1 2D&3D BB and Seg masks
+load('../OFFICIAL_SUNRGBD/SUNRGBDtoolbox/Metadata/SUNRGBDMeta.mat')
+% load('./Metadata/SUNRGBD2Dseg.mat')
+
+%% Create folders
+det_label_folder = '../sunrgbd_trainval/label_v1/';
+mkdir(det_label_folder);
+%% Read
+for imageId = 1:10335
+    imageId
+try
+data = SUNRGBDMeta(imageId);
+data.depthpath(1:16) = '';
+data.depthpath = strcat('../OFFICIAL_SUNRGBD/SUNRGBD', data.depthpath);
+data.rgbpath(1:16) = '';
+data.rgbpath = strcat('../OFFICIAL_SUNRGBD/SUNRGBD', data.rgbpath);
+
+% MAT files are 3x smaller than TXT files. In Python we can use
+% scipy.io.loadmat('xxx.mat')['points3d_rgb'] to load the data.
+mat_filename = strcat(num2str(imageId,'%06d'), '.mat');
+txt_filename = strcat(num2str(imageId,'%06d'), '.txt');
+
+% Write 2D and 3D box label
+data2d = data;
+fid = fopen(strcat(det_label_folder, txt_filename), 'w');
+for j = 1:length(data.groundtruth3DBB)
+    centroid = data.groundtruth3DBB(j).centroid;
+    classname = data.groundtruth3DBB(j).classname;
+    orientation = data.groundtruth3DBB(j).orientation;
+    coeffs = abs(data.groundtruth3DBB(j).coeffs);
+    box2d = data2d.groundtruth2DBB(j).gtBb2D;
+    fprintf(fid, '%s %d %d %d %d %f %f %f %f %f %f %f %f\n', classname, box2d(1), box2d(2), box2d(3), box2d(4), centroid(1), centroid(2), centroid(3), coeffs(1), coeffs(2), coeffs(3), orientation(1), orientation(2));
+end
+fclose(fid);
+
+catch
+end
+
+end

data/sunrgbd/matlab/extract_rgbd_data_v2.m

+% Copyright (c) Facebook, Inc. and its affiliates.
+%
+% This source code is licensed under the MIT license found in the
+% LICENSE file in the root directory of this source tree.
+
+%% Dump SUNRGBD data to our format
+% for each sample, we have RGB image, 2d boxes.
+% point cloud (in camera coordinate), calibration and 3d boxes.
+%
+% Compared to extract_rgbd_data.m in frustum_pointents, use v2 2D and 3D
+% bboxes.
+%
+% Author: Charles R. Qi
+%
+clear; close all; clc;
+addpath(genpath('.'))
+addpath('../OFFICIAL_SUNRGBD/SUNRGBDtoolbox/readData')
+%% V1 2D&3D BB and Seg masks
+% load('./Metadata/SUNRGBDMeta.mat')
+% load('./Metadata/SUNRGBD2Dseg.mat')
+
+%% V2 3DBB annotations (overwrites SUNRGBDMeta)
+load('../OFFICIAL_SUNRGBD/SUNRGBDMeta3DBB_v2.mat');
+load('../OFFICIAL_SUNRGBD/SUNRGBDMeta2DBB_v2.mat');
+%% Create folders
+depth_folder = '../sunrgbd_trainval/depth/';
+image_folder = '../sunrgbd_trainval/image/';
+calib_folder = '../sunrgbd_trainval/calib/';
+det_label_folder = '../sunrgbd_trainval/label/';
+seg_label_folder = '../sunrgbd_trainval/seg_label/';
+mkdir(depth_folder);
+mkdir(image_folder);
+mkdir(calib_folder);
+mkdir(det_label_folder);
+mkdir(seg_label_folder);
+%% Read
+parfor imageId = 1:10335
+    imageId
+try
+data = SUNRGBDMeta(imageId);
+data.depthpath(1:16) = '';
+data.depthpath = strcat('../OFFICIAL_SUNRGBD', data.depthpath);
+data.rgbpath(1:16) = '';
+data.rgbpath = strcat('../OFFICIAL_SUNRGBD', data.rgbpath);
+
+% Write point cloud in depth map
+[rgb,points3d,depthInpaint,imsize]=read3dPoints(data);
+rgb(isnan(points3d(:,1)),:) = [];
+points3d(isnan(points3d(:,1)),:) = [];
+points3d_rgb = [points3d, rgb];
+
+% MAT files are 3x smaller than TXT files. In Python we can use
+% scipy.io.loadmat('xxx.mat')['points3d_rgb'] to load the data.
+mat_filename = strcat(num2str(imageId,'%06d'), '.mat');
+txt_filename = strcat(num2str(imageId,'%06d'), '.txt');
+parsave(strcat(depth_folder, mat_filename), points3d_rgb);
+
+% Write images
+copyfile(data.rgbpath, sprintf('%s/%06d.jpg', image_folder, imageId));
+
+% Write calibration
+dlmwrite(strcat(calib_folder, txt_filename), data.Rtilt(:)', 'delimiter', ' ');
+dlmwrite(strcat(calib_folder, txt_filename), data.K(:)', 'delimiter', ' ', '-append');
+
+% Write 2D and 3D box label
+data2d = SUNRGBDMeta2DBB(imageId);
+fid = fopen(strcat(det_label_folder, txt_filename), 'w');
+for j = 1:length(data.groundtruth3DBB)
+    centroid = data.groundtruth3DBB(j).centroid;
+    classname = data.groundtruth3DBB(j).classname;
+    orientation = data.groundtruth3DBB(j).orientation;
+    coeffs = abs(data.groundtruth3DBB(j).coeffs);
+    box2d = data2d.groundtruth2DBB(j).gtBb2D;
+    assert(strcmp(data2d.groundtruth2DBB(j).classname, classname));
+    fprintf(fid, '%s %d %d %d %d %f %f %f %f %f %f %f %f\n', classname, box2d(1), box2d(2), box2d(3), box2d(4), centroid(1), centroid(2), centroid(3), coeffs(1), coeffs(2), coeffs(3), orientation(1), orientation(2));
+end
+fclose(fid);
+
+catch
+end
+
+end
+
+function parsave(filename, instance)
+save(filename, 'instance');
+end

data/sunrgbd/matlab/extract_split.m

+% Modified from
+% https://github.com/facebookresearch/votenet/blob/master/sunrgbd/matlab/extract_split.m
+% Copyright (c) Facebook, Inc. and its affiliates.
+%
+% This source code is licensed under the MIT license found in the
+% LICENSE file in the root directory of this source tree.
+
+%% Dump train/val split.
+% Author: Charles R. Qi
+
+addpath('../OFFICIAL_SUNRGBD/SUNRGBDtoolbox')
+
+%% Construct Hash Map
+hash_train = java.util.Hashtable;
+hash_val = java.util.Hashtable;
+
+split = load('../OFFICIAL_SUNRGBD/SUNRGBDtoolbox/traintestSUNRGBD/allsplit.mat');
+
+N_train = length(split.alltrain);
+N_val = length(split.alltest);
+
+for i = 1:N_train
+    folder_path = split.alltrain{i};
+    folder_path(1:16) = '';
+    hash_train.put(folder_path,0);
+end
+for i = 1:N_val
+    folder_path = split.alltest{i};
+    folder_path(1:16) = '';
+    hash_val.put(folder_path,0);
+end
+
+%% Map data to train or val set.
+load('../OFFICIAL_SUNRGBD/SUNRGBDMeta3DBB_v2.mat');
+if exist('../sunrgbd_trainval','dir')==0
+    mkdir('../sunrgbd_trainval');
+end
+fid_train = fopen('../sunrgbd_trainval/train_data_idx.txt', 'w');
+fid_val = fopen('../sunrgbd_trainval/val_data_idx.txt', 'w');
+
+for imageId = 1:10335
+    data = SUNRGBDMeta(imageId);
+    depthpath = data.depthpath;
+    depthpath(1:16) = '';
+    [filepath,name,ext] = fileparts(depthpath);
+    [filepath,name,ext] = fileparts(filepath);
+    if hash_train.containsKey(filepath)
+        fprintf(fid_train, '%d\n', imageId);
+    elseif hash_val.containsKey(filepath)
+        fprintf(fid_val, '%d\n', imageId);
+    else
+        a = 1;
+    end
+end
+fclose(fid_train);
+fclose(fid_val);

data/sunrgbd/sunrgbd_data.py

+# Modified from
+# https://github.com/facebookresearch/votenet/blob/master/sunrgbd/sunrgbd_data.py
+# Copyright (c) Facebook, Inc. and its affiliates.
+#
+# This source code is licensed under the MIT license found in the
+# LICENSE file in the root directory of this source tree.
+''' Helper class and functions for loading SUN RGB-D objects
+
+Author: Charles R. Qi
+Date: December, 2018
+
+Note: removed unused code for frustum preparation.
+Changed a way for data visualization (removed depdency on mayavi).
+Load depth with scipy.io
+'''
+
+import argparse
+import os
+import sys
+
+import numpy as np
+import sunrgbd_utils
+
+BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+sys.path.append(BASE_DIR)
+sys.path.append(os.path.join(BASE_DIR, '../utils/'))
+
+DEFAULT_TYPE_WHITELIST = [
+    'bed', 'table', 'sofa', 'chair', 'toilet', 'desk', 'dresser',
+    'night_stand', 'bookshelf', 'bathtub'
+]
+
+
+def random_sampling(pc, num_sample, replace=None, return_choices=False):
+    """ Input is NxC, output is num_samplexC
+    """
+    if replace is None:
+        replace = (pc.shape[0] < num_sample)
+    choices = np.random.choice(pc.shape[0], num_sample, replace=replace)
+    if return_choices:
+        return pc[choices], choices
+    else:
+        return pc[choices]
+
+
+class sunrgbd_object(object):
+    """Surrgbd object.
+
+    Load and parse object data.
+
+    Args:
+        root_dir(str): Root directory.
+        split(str): Training or testing.
+            Default: 'training.
+        use_v1(bool): Whether to use v1.
+            Default(False).
+    """
+
+    def __init__(self, root_dir, split='training', use_v1=False):
+        self.root_dir = root_dir
+        self.split = split
+        assert (self.split == 'training')
+        self.split_dir = os.path.join(root_dir)
+
+        if split == 'training':
+            self.num_samples = 10335
+        elif split == 'testing':
+            self.num_samples = 2860
+        else:
+            print('Unknown split: %s' % (split))
+            exit(-1)
+
+        self.image_dir = os.path.join(self.split_dir, 'image')
+        self.calib_dir = os.path.join(self.split_dir, 'calib')
+        self.depth_dir = os.path.join(self.split_dir, 'depth')
+        if use_v1:
+            self.label_dir = os.path.join(self.split_dir, 'label_v1')
+        else:
+            self.label_dir = os.path.join(self.split_dir, 'label')
+
+    def __len__(self):
+        return self.num_samples
+
+    def get_image(self, idx):
+        img_filename = os.path.join(self.image_dir, '%06d.jpg' % (idx))
+        return sunrgbd_utils.load_image(img_filename)
+
+    def get_depth(self, idx):
+        depth_filename = os.path.join(self.depth_dir, '%06d.mat' % (idx))
+        return sunrgbd_utils.load_depth_points_mat(depth_filename)
+
+    def get_calibration(self, idx):
+        calib_filename = os.path.join(self.calib_dir, '%06d.txt' % (idx))
+        return sunrgbd_utils.SUNRGBD_Calibration(calib_filename)
+
+    def get_label_objects(self, idx):
+        label_filename = os.path.join(self.label_dir, '%06d.txt' % (idx))
+        return sunrgbd_utils.read_sunrgbd_label(label_filename)
+
+
+def extract_sunrgbd_data(idx_filename,
+                         split,
+                         output_folder,
+                         num_point=20000,
+                         type_whitelist=DEFAULT_TYPE_WHITELIST,
+                         save_votes=False,
+                         use_v1=False,
+                         skip_empty_scene=True):
+    """Extract scene point clouds and
+            bounding boxes (centroids, box sizes, heading angles,
+            semantic classes). Dumped point clouds and boxes are in
+            upright depth coord.
+
+    Args:
+        idx_filename: a TXT file where each line is an int number (index)
+        split: training or testing
+        save_votes: whether to compute and save Ground truth votes.
+        use_v1: use the SUN RGB-D V1 data
+        skip_empty_scene: if True, skip scenes that contain no object
+        (no objet in whitelist)
+
+    Dumps:
+        <id>_pc.npz of (N,6) where N is for number of subsampled points
+            and 6 is for XYZ and RGB (in 0~1) in upright depth coord
+        <id>_bbox.npy of (K,8) where K is the number of objects, 8 is for
+            centroids (cx,cy,cz), dimension (l,w,h), heanding_angle and
+            semantic_class
+        <id>_votes.npz of (N,10) with 0/1 indicating whether the point
+            belongs to an object, then three sets of GT votes for up to
+            three objects. If the point is only in one object's OBB, then
+            the three GT votes are the same.
+    """
+    dataset = sunrgbd_object('./sunrgbd_trainval', split, use_v1=use_v1)
+    data_idx_list = [int(line.rstrip()) for line in open(idx_filename)]
+
+    if not os.path.exists(output_folder):
+        os.mkdir(output_folder)
+
+    for data_idx in data_idx_list:
+        print('------------- ', data_idx)
+        objects = dataset.get_label_objects(data_idx)
+
+        if skip_empty_scene and \
+                (len(objects) == 0 or
+                 len([obj for obj in objects if
+                      obj.classname in type_whitelist]) == 0):
+            continue
+
+        object_list = []
+        for obj in objects:
+            if obj.classname not in type_whitelist:
+                continue
+            obb = np.zeros((8))
+            obb[0:3] = obj.centroid
+            obb[3:6] = np.array([obj.length, obj.width, obj.height])
+            obb[6] = obj.heading_angle
+            obb[7] = sunrgbd_utils.type2class[obj.classname]
+            object_list.append(obb)
+        if len(object_list) == 0:
+            obbs = np.zeros((0, 8))
+        else:
+            obbs = np.vstack(object_list)  # (K,8)
+
+        pc_upright_depth = dataset.get_depth(data_idx)
+        pc_upright_depth_subsampled = random_sampling(pc_upright_depth,
+                                                      num_point)
+
+        np.savez_compressed(
+            os.path.join(output_folder, '%06d_pc.npz' % (data_idx)),
+            pc=pc_upright_depth_subsampled)
+        np.save(
+            os.path.join(output_folder, '%06d_bbox.npy' % (data_idx)), obbs)
+
+        if save_votes:
+            N = pc_upright_depth_subsampled.shape[0]
+            point_votes = np.zeros((N, 10))  # 3 votes and 1 vote mask
+            point_vote_idx = np.zeros(
+                (N)).astype(np.int32)  # in the range of [0,2]
+            indices = np.arange(N)
+            for obj in objects:
+                if obj.classname not in type_whitelist:
+                    continue
+                try:
+                    # Find all points in this object's OBB
+                    box3d_pts_3d = sunrgbd_utils.my_compute_box_3d(
+                        obj.centroid,
+                        np.array([obj.length, obj.width, obj.height]),
+                        obj.heading_angle)
+                    pc_in_box3d, inds = sunrgbd_utils.extract_pc_in_box3d(
+                        pc_upright_depth_subsampled, box3d_pts_3d)
+                    point_votes[inds, 0] = 1
+                    votes = np.expand_dims(obj.centroid, 0) - pc_in_box3d[:,
+                                                                          0:3]
+                    sparse_inds = indices[inds]
+                    for i in range(len(sparse_inds)):
+                        j = sparse_inds[i]
+                        point_votes[j,
+                                    int(point_vote_idx[j] * 3 +
+                                        1):int((point_vote_idx[j] + 1) * 3 +
+                                               1)] = votes[i, :]
+                        # Populate votes with the fisrt vote
+                        if point_vote_idx[j] == 0:
+                            point_votes[j, 4:7] = votes[i, :]
+                            point_votes[j, 7:10] = votes[i, :]
+                    point_vote_idx[inds] = np.minimum(2,
+                                                      point_vote_idx[inds] + 1)
+                except Exception:
+                    print('ERROR ----', data_idx, obj.classname)
+            np.savez_compressed(
+                os.path.join(output_folder, '%06d_votes.npz' % (data_idx)),
+                point_votes=point_votes)
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        '--compute_median_size',
+        action='store_true',
+        help='Compute median 3D bounding box sizes for each class.')
+    parser.add_argument(
+        '--gen_v1_data', action='store_true', help='Generate V1 dataset.')
+    parser.add_argument(
+        '--gen_v2_data', action='store_true', help='Generate V2 dataset.')
+    args = parser.parse_args()
+
+    if args.gen_v1_data:
+        extract_sunrgbd_data(
+            os.path.join(BASE_DIR, 'sunrgbd_trainval/train_data_idx.txt'),
+            split='training',
+            output_folder=os.path.join(BASE_DIR,
+                                       'sunrgbd_pc_bbox_votes_50k_v1_train'),
+            save_votes=True,
+            num_point=50000,
+            use_v1=True,
+            skip_empty_scene=False)
+        extract_sunrgbd_data(
+            os.path.join(BASE_DIR, 'sunrgbd_trainval/val_data_idx.txt'),
+            split='training',
+            output_folder=os.path.join(BASE_DIR,
+                                       'sunrgbd_pc_bbox_votes_50k_v1_val'),
+            save_votes=True,
+            num_point=50000,
+            use_v1=True,
+            skip_empty_scene=False)
+
+    if args.gen_v2_data:
+        extract_sunrgbd_data(
+            os.path.join(BASE_DIR, 'sunrgbd_trainval/train_data_idx.txt'),
+            split='training',
+            output_folder=os.path.join(BASE_DIR,
+                                       'sunrgbd_pc_bbox_votes_50k_v2_train'),
+            save_votes=True,
+            num_point=50000,
+            use_v1=False,
+            skip_empty_scene=False)
+        extract_sunrgbd_data(
+            os.path.join(BASE_DIR, 'sunrgbd_trainval/val_data_idx.txt'),
+            split='training',
+            output_folder=os.path.join(BASE_DIR,
+                                       'sunrgbd_pc_bbox_votes_50k_v2_val'),
+            save_votes=True,
+            num_point=50000,
+            use_v1=False,
+            skip_empty_scene=False)

data/sunrgbd/sunrgbd_utils.py

+# Modified from
+# https://github.com/facebookresearch/votenet/blob/master/sunrgbd/sunrgbd_utils.py
+# Copyright (c) Facebook, Inc. and its affiliates.
+#
+# This source code is licensed under the MIT license found in the
+# LICENSE file in the root directory of this source tree.
+"""Provides Python helper function to read My SUNRGBD dataset.
+
+Author: Charles R. Qi
+Date: October, 2017
+
+Updated by Charles R. Qi
+Date: December, 2018
+Note: removed basis loading.
+"""
+
+import cv2
+import numpy as np
+import scipy.io as sio
+
+type2class = {
+    'bed': 0,
+    'table': 1,
+    'sofa': 2,
+    'chair': 3,
+    'toilet': 4,
+    'desk': 5,
+    'dresser': 6,
+    'night_stand': 7,
+    'bookshelf': 8,
+    'bathtub': 9
+}
+class2type = {type2class[t]: t for t in type2class}
+
+
+def flip_axis_to_camera(pc):
+    """Flip axis to camera.
+
+    Flip X-right,Y-forward,Z-up to X-right,Y-down,Z-forward.
+
+    Args:
+        pc(ndarray): points in depth axis.
+
+    Returns:
+        ndarray: points in camera  axis.
+    """
+    pc2 = np.copy(pc)
+    pc2[:, [0, 1, 2]] = pc2[:, [0, 2, 1]]  # cam X,Y,Z = depth X,-Z,Y
+    pc2[:, 1] *= -1
+    return pc2
+
+
+def flip_axis_to_depth(pc):
+    pc2 = np.copy(pc)
+    pc2[:, [0, 1, 2]] = pc2[:, [0, 2, 1]]  # depth X,Y,Z = cam X,Z,-Y
+    pc2[:, 2] *= -1
+    return pc2
+
+
+class SUNObject3d(object):
+
+    def __init__(self, line):
+        data = line.split(' ')
+        data[1:] = [float(x) for x in data[1:]]
+        self.classname = data[0]
+        self.xmin = data[1]
+        self.ymin = data[2]
+        self.xmax = data[1] + data[3]
+        self.ymax = data[2] + data[4]
+        self.box2d = np.array([self.xmin, self.ymin, self.xmax, self.ymax])
+        self.centroid = np.array([data[5], data[6], data[7]])
+        self.unused_dimension = np.array([data[8], data[9], data[10]])
+        self.width = data[8]
+        self.length = data[9]
+        self.height = data[10]
+        self.orientation = np.zeros((3, ))
+        self.orientation[0] = data[11]
+        self.orientation[1] = data[12]
+        self.heading_angle = -1 * np.arctan2(self.orientation[1],
+                                             self.orientation[0])
+
+
+class SUNRGBD_Calibration(object):
+    """Calibration matrices and utils
+
+    We define five coordinate system in SUN RGBD dataset:
+
+        camera coodinate:
+            Z is forward, Y is downward, X is rightward.
+
+        depth coordinate:
+            Just change axis order and flip up-down axis from camera coord.
+
+        upright depth coordinate: tilted depth coordinate by Rtilt such that
+            Z is gravity direction, Z is up-axis, Y is forward,
+            X is right-ward.
+
+        upright camera coordinate:
+            Just change axis order and flip up-down axis from upright.
+                depth coordinate
+
+        image coordinate:
+            ----> x-axis (u)
+           |
+           v
+            y-axis (v)
+
+        depth points are stored in upright depth coordinate.
+        labels for 3d box (basis, centroid, size) are in upright
+            depth coordinate.
+        2d boxes are in image coordinate
+
+        We generate frustum point cloud and 3d box
+        in upright camera coordinate.
+
+    Args:
+        calib_filepath(str): Path of the calib file.
+    """
+
+    def __init__(self, calib_filepath):
+        lines = [line.rstrip() for line in open(calib_filepath)]
+        Rtilt = np.array([float(x) for x in lines[0].split(' ')])
+        self.Rtilt = np.reshape(Rtilt, (3, 3), order='F')
+        K = np.array([float(x) for x in lines[1].split(' ')])
+        self.K = np.reshape(K, (3, 3), order='F')
+        self.f_u = self.K[0, 0]
+        self.f_v = self.K[1, 1]
+        self.c_u = self.K[0, 2]
+        self.c_v = self.K[1, 2]
+
+    def project_upright_depth_to_camera(self, pc):
+        """Convert pc coordinate from depth to image.
+
+        Args:
+            pc(ndarray): Point cloud in depth coordinate.
+
+        Returns:
+            pc(ndarray): Point cloud in camera coordinate.
+        """
+        # Project upright depth to depth coordinate
+        pc2 = np.dot(np.transpose(self.Rtilt), np.transpose(pc[:,
+                                                               0:3]))  # (3,n)
+        return flip_axis_to_camera(np.transpose(pc2))
+
+    def project_upright_depth_to_image(self, pc):
+        """Convert pc coordinate from depth to image.
+
+        Args:
+            pc(ndarray): Point cloud in depth coordinate.
+
+        Returns:
+            ndarray: [N, 2] uv.
+            ndarray: [n,] depth.
+        """
+        pc2 = self.project_upright_depth_to_camera(pc)
+        uv = np.dot(pc2, np.transpose(self.K))  # (n,3)
+        uv[:, 0] /= uv[:, 2]
+        uv[:, 1] /= uv[:, 2]
+        return uv[:, 0:2], pc2[:, 2]
+
+    def project_image_to_camera(self, uv_depth):
+        n = uv_depth.shape[0]
+        x = ((uv_depth[:, 0] - self.c_u) * uv_depth[:, 2]) / self.f_u
+        y = ((uv_depth[:, 1] - self.c_v) * uv_depth[:, 2]) / self.f_v
+        pts_3d_camera = np.zeros((n, 3))
+        pts_3d_camera[:, 0] = x
+        pts_3d_camera[:, 1] = y
+        pts_3d_camera[:, 2] = uv_depth[:, 2]
+        return pts_3d_camera
+
+
+def rotz(t):
+    """Rotation about the z-axis.
+
+    Args:
+        t(float): Heading angle.
+
+    Returns:
+        ndarray: Transforation matrix
+    """
+    c = np.cos(t)
+    s = np.sin(t)
+    return np.array([[c, -s, 0], [s, c, 0], [0, 0, 1]])
+
+
+def transform_from_rot_trans(R, t):
+    """Transforation matrix from rotation matrix and translation vector.
+
+    Args:
+        R(ndarray): Rotation matrix.
+        t(ndarray): Translation vector.
+
+    Returns:
+        ndarray: Transforation matrix.
+    """
+    R = R.reshape(3, 3)
+    t = t.reshape(3, 1)
+    return np.vstack((np.hstack([R, t]), [0, 0, 0, 1]))
+
+
+def read_sunrgbd_label(label_filename):
+    lines = [line.rstrip() for line in open(label_filename)]
+    objects = [SUNObject3d(line) for line in lines]
+    return objects
+
+
+def load_image(img_filename):
+    return cv2.imread(img_filename)
+
+
+def load_depth_points(depth_filename):
+    depth = np.loadtxt(depth_filename)
+    return depth
+
+
+def load_depth_points_mat(depth_filename):
+    depth = sio.loadmat(depth_filename)['instance']
+    return depth
+
+
+def in_hull(p, hull):
+    from scipy.spatial import Delaunay
+    if not isinstance(hull, Delaunay):
+        hull = Delaunay(hull)
+    return hull.find_simplex(p) >= 0
+
+
+def extract_pc_in_box3d(pc, box3d):
+    """Extract point cloud in box3d.
+
+    Args:
+        pc(ndarray): [N, 3] Point cloud.
+        box3d(ndarray): [8,3] 3d box.
+
+    Returns:
+        ndarray: Selected point cloud.
+        ndarray: Indices of selected point cloud.
+    """
+    box3d_roi_inds = in_hull(pc[:, 0:3], box3d)
+    return pc[box3d_roi_inds, :], box3d_roi_inds
+
+
+def my_compute_box_3d(center, size, heading_angle):
+    R = rotz(-1 * heading_angle)
+    l, w, h = size
+    x_corners = [-l, l, l, -l, -l, l, l, -l]
+    y_corners = [w, w, -w, -w, w, w, -w, -w]
+    z_corners = [h, h, h, h, -h, -h, -h, -h]
+    corners_3d = np.dot(R, np.vstack([x_corners, y_corners, z_corners]))
+    corners_3d[0, :] += center[0]
+    corners_3d[1, :] += center[1]
+    corners_3d[2, :] += center[2]
+    return np.transpose(corners_3d)
+
+
+def compute_box_3d(obj, calib):
+    """Takes an object and a projection matrix (P) and projects the 3d
+        bounding box into the image plane.
+
+    Args:
+        obj(SUNObject3d): Instance of SUNObject3d.
+        calib(SUNRGBD_Calibration): Instance of SUNRGBD_Calibration.
+
+    Returns:
+        ndarray: [8,2] array in image coord.
+        corners_3d: [8,3] array in in upright depth coord.
+    """
+    center = obj.centroid
+
+    # compute rotational matrix around yaw axis
+    R = rotz(-1 * obj.heading_angle)
+
+    # 3d bounding box dimensions
+    length = obj.length  # along heading arrow
+    width = obj.width  # perpendicular to heading arrow
+    height = obj.height
+
+    # rotate and translate 3d bounding box
+    x_corners = [
+        -length, length, length, -length, -length, length, length, -length
+    ]
+    y_corners = [width, width, -width, -width, width, width, -width, -width]
+    z_corners = [
+        height, height, height, height, -height, -height, -height, -height
+    ]
+    corners_3d = np.dot(R, np.vstack([x_corners, y_corners, z_corners]))
+    corners_3d[0, :] += center[0]
+    corners_3d[1, :] += center[1]
+    corners_3d[2, :] += center[2]
+
+    # project the 3d bounding box into the image plane
+    corners_2d, _ = calib.project_upright_depth_to_image(
+        np.transpose(corners_3d))
+    return corners_2d, np.transpose(corners_3d)