ScanNet data set download

Preface

The author, a novice CV player, was really worried about obtaining the ScanNet data set. Fortunately, he succeeded in obtaining it in the end! Here I will record the detailed process of obtaining the data set in the past two days. I hope it can help more people and learn and progress together! (o( ￣▽￣ )ブ)

1. Introduction to data sets

ScanNet is an RGB-D video dataset containing 2.5 million views over 1,500 scans annotated using 3D camera poses, surface reconstruction, and instance-level semantic segmentation.

Official website:https://github.com/ScanNet/ScanNet

2. Data set acquisition

To apply for a data set, application method: ScanNet Terms of Use to [email protected]
After applying, you will receive two codes. In order to save everyone's application time, I will simply post the code here.
download_scannet.py

#!/usr/bin/env python
# Downloads ScanNet public data release
# Run with ./download-scannet.py (or python download-scannet.py on Windows)
# -*- coding: utf-8 -*-
import argparse
import os
# import urllib.request (for python3)
import urllib
import tempfile

BASE_URL = 'http://kaldir.vc.in.tum.de/scannet/'
TOS_URL = BASE_URL + 'ScanNet_TOS.pdf'
FILETYPES = ['.aggregation.json', '.sens', '.txt', '_vh_clean.ply', '_vh_clean_2.0.010000.segs.json', '_vh_clean_2.ply', '_vh_clean.segs.json', '_vh_clean.aggregation.json', '_vh_clean_2.labels.ply', '_2d-instance.zip', '_2d-instance-filt.zip', '_2d-label.zip', '_2d-label-filt.zip']
FILETYPES_TEST = ['.sens', '.txt', '_vh_clean.ply', '_vh_clean_2.ply']
PREPROCESSED_FRAMES_FILE = ['scannet_frames_25k.zip', '5.6GB']
TEST_FRAMES_FILE = ['scannet_frames_test.zip', '610MB']
LABEL_MAP_FILES = ['scannetv2-labels.combined.tsv', 'scannet-labels.combined.tsv']
RELEASES = ['v2/scans', 'v1/scans']
RELEASES_TASKS = ['v2/tasks', 'v1/tasks']
RELEASES_NAMES = ['v2', 'v1']
RELEASE = RELEASES[0]
RELEASE_TASKS = RELEASES_TASKS[0]
RELEASE_NAME = RELEASES_NAMES[0]
LABEL_MAP_FILE = LABEL_MAP_FILES[0]
RELEASE_SIZE = '1.2TB'
V1_IDX = 1


def get_release_scans(release_file):
    #scan_lines = urllib.request.urlopen(release_file)
    scan_lines = urllib.urlopen(release_file)
    scans = []
    for scan_line in scan_lines:
        scan_id = scan_line.decode('utf8').rstrip('\n')
        scans.append(scan_id)
    return scans


def download_release(release_scans, out_dir, file_types, use_v1_sens):
    if len(release_scans) == 0:
        return
    print('Downloading ScanNet ' + RELEASE_NAME + ' release to ' + out_dir + '...')
    for scan_id in release_scans:
        scan_out_dir = os.path.join(out_dir, scan_id)
        download_scan(scan_id, scan_out_dir, file_types, use_v1_sens)
    print('Downloaded ScanNet ' + RELEASE_NAME + ' release.')


def download_file(url, out_file):
    out_dir = os.path.dirname(out_file)
    if not os.path.isdir(out_dir):
        os.makedirs(out_dir)
    if not os.path.isfile(out_file):
        print('\t' + url + ' > ' + out_file)
        fh, out_file_tmp = tempfile.mkstemp(dir=out_dir)
        f = os.fdopen(fh, 'w')
        f.close()
        #urllib.request.urlretrieve(url, out_file_tmp)
        urllib.urlretrieve(url, out_file_tmp)
        os.rename(out_file_tmp, out_file)
    else:
        print('WARNING: skipping download of existing file ' + out_file)

def download_scan(scan_id, out_dir, file_types, use_v1_sens):
    print('Downloading ScanNet ' + RELEASE_NAME + ' scan ' + scan_id + ' ...')
    if not os.path.isdir(out_dir):
        os.makedirs(out_dir)
    for ft in file_types:
        v1_sens = use_v1_sens and ft == '.sens'
        url = BASE_URL + RELEASE + '/' + scan_id + '/' + scan_id + ft if not v1_sens else BASE_URL + RELEASES[V1_IDX] + '/' + scan_id + '/' + scan_id + ft
        out_file = out_dir + '/' + scan_id + ft
        download_file(url, out_file)
    print('Downloaded scan ' + scan_id)


def download_task_data(out_dir):
    print('Downloading ScanNet v1 task data...')
    files = [
        LABEL_MAP_FILES[V1_IDX], 'obj_classification/data.zip',
        'obj_classification/trained_models.zip', 'voxel_labeling/data.zip',
        'voxel_labeling/trained_models.zip'
    ]
    for file in files:
        url = BASE_URL + RELEASES_TASKS[V1_IDX] + '/' + file
        localpath = os.path.join(out_dir, file)
        localdir = os.path.dirname(localpath)
        if not os.path.isdir(localdir):
          os.makedirs(localdir)
        download_file(url, localpath)
    print('Downloaded task data.')


def download_label_map(out_dir):
    print('Downloading ScanNet ' + RELEASE_NAME + ' label mapping file...')
    files = [ LABEL_MAP_FILE ]
    for file in files:
        url = BASE_URL + RELEASE_TASKS + '/' + file
        localpath = os.path.join(out_dir, file)
        localdir = os.path.dirname(localpath)
        if not os.path.isdir(localdir):
          os.makedirs(localdir)
        download_file(url, localpath)
    print('Downloaded ScanNet ' + RELEASE_NAME + ' label mapping file.')


def main():
    parser = argparse.ArgumentParser(description='Downloads ScanNet public data release.')
    parser.add_argument('-o', '--out_dir', required=True, help='directory in which to download')
    parser.add_argument('--task_data', action='store_true', help='download task data (v1)')
    parser.add_argument('--label_map', action='store_true', help='download label map file')
    parser.add_argument('--v1', action='store_true', help='download ScanNet v1 instead of v2')
    parser.add_argument('--id', help='specific scan id to download')
    parser.add_argument('--preprocessed_frames', action='store_true', help='download preprocessed subset of ScanNet frames (' + PREPROCESSED_FRAMES_FILE[1] + ')')
    parser.add_argument('--test_frames_2d', action='store_true', help='download 2D test frames (' + TEST_FRAMES_FILE[1] + '; also included with whole dataset download)')
    parser.add_argument('--type', help='specific file type to download (.aggregation.json, .sens, .txt, _vh_clean.ply, _vh_clean_2.0.010000.segs.json, _vh_clean_2.ply, _vh_clean.segs.json, _vh_clean.aggregation.json, _vh_clean_2.labels.ply, _2d-instance.zip, _2d-instance-filt.zip, _2d-label.zip, _2d-label-filt.zip)')
    args = parser.parse_args()

    print('By pressing any key to continue you confirm that you have agreed to the ScanNet terms of use as described at:')
    print(TOS_URL)
    print('***')
    print('Press any key to continue, or CTRL-C to exit.')
    key = raw_input('')

    if args.v1:
        global RELEASE
        global RELEASE_TASKS
        global RELEASE_NAME
        global LABEL_MAP_FILE
        RELEASE = RELEASES[V1_IDX]
        RELEASE_TASKS = RELEASES_TASKS[V1_IDX]
        RELEASE_NAME = RELEASES_NAMES[V1_IDX]
        LABEL_MAP_FILE = LABEL_MAP_FILES[V1_IDX]

    release_file = BASE_URL + RELEASE + '.txt'
    release_scans = get_release_scans(release_file)
    file_types = FILETYPES;
    release_test_file = BASE_URL + RELEASE + '_test.txt'
    release_test_scans = get_release_scans(release_test_file)
    file_types_test = FILETYPES_TEST;
    out_dir_scans = os.path.join(args.out_dir, 'scans')
    out_dir_test_scans = os.path.join(args.out_dir, 'scans_test')
    out_dir_tasks = os.path.join(args.out_dir, 'tasks')

    if args.type:  # download file type
        file_type = args.type
        if file_type not in FILETYPES:
            print('ERROR: Invalid file type: ' + file_type)
            return
        file_types = [file_type]
        if file_type in FILETYPES_TEST:
            file_types_test = [file_type]
        else:
            file_types_test = []
    if args.task_data:  # download task data
        download_task_data(out_dir_tasks)
    elif args.label_map:  # download label map file
        download_label_map(args.out_dir)
    elif args.preprocessed_frames:  # download preprocessed scannet_frames_25k.zip file
        if args.v1:
            print('ERROR: Preprocessed frames only available for ScanNet v2')
        print('You are downloading the preprocessed subset of frames ' + PREPROCESSED_FRAMES_FILE[0] + ' which requires ' + PREPROCESSED_FRAMES_FILE[1] + ' of space.')
        download_file(os.path.join(BASE_URL, RELEASE_TASKS, PREPROCESSED_FRAMES_FILE[0]), os.path.join(out_dir_tasks, PREPROCESSED_FRAMES_FILE[0]))
    elif args.test_frames_2d:  # download test scannet_frames_test.zip file
        if args.v1:
            print('ERROR: 2D test frames only available for ScanNet v2')
        print('You are downloading the 2D test set ' + TEST_FRAMES_FILE[0] + ' which requires ' + TEST_FRAMES_FILE[1] + ' of space.')
        download_file(os.path.join(BASE_URL, RELEASE_TASKS, TEST_FRAMES_FILE[0]), os.path.join(out_dir_tasks, TEST_FRAMES_FILE[0]))
    elif args.id:  # download single scan
        scan_id = args.id
        is_test_scan = scan_id in release_test_scans
        if scan_id not in release_scans and (not is_test_scan or args.v1):
            print('ERROR: Invalid scan id: ' + scan_id)
        else:
            out_dir = os.path.join(out_dir_scans, scan_id) if not is_test_scan else os.path.join(out_dir_test_scans, scan_id)
            scan_file_types = file_types if not is_test_scan else file_types_test
            use_v1_sens = not is_test_scan
            if not is_test_scan and not args.v1 and '.sens' in scan_file_types:
                print('Note: ScanNet v2 uses the same .sens files as ScanNet v1: Press \'n\' to exclude downloading .sens files for each scan')
                key = raw_input('')
                if key.strip().lower() == 'n':
                    scan_file_types.remove('.sens')
            download_scan(scan_id, out_dir, scan_file_types, use_v1_sens)
    else:  # download entire release
        if len(file_types) == len(FILETYPES):
            print('WARNING: You are downloading the entire ScanNet ' + RELEASE_NAME + ' release which requires ' + RELEASE_SIZE + ' of space.')
        else:
            print('WARNING: You are downloading all ScanNet ' + RELEASE_NAME + ' scans of type ' + file_types[0])
        print('Note that existing scan directories will be skipped. Delete partially downloaded directories to re-download.')
        print('***')
        print('Press any key to continue, or CTRL-C to exit.')
        key = raw_input('')
        if not args.v1 and '.sens' in file_types:
            print('Note: ScanNet v2 uses the same .sens files as ScanNet v1: Press \'n\' to exclude downloading .sens files for each scan')
            key = raw_input('')
            if key.strip().lower() == 'n':
                file_types.remove('.sens')
        download_release(release_scans, out_dir_scans, file_types, use_v1_sens=True)
        if not args.v1:
            download_label_map(args.out_dir)
            download_release(release_test_scans, out_dir_test_scans, file_types_test, use_v1_sens=False)
            download_file(os.path.join(BASE_URL, RELEASE_TASKS, TEST_FRAMES_FILE[0]), os.path.join(out_dir_tasks, TEST_FRAMES_FILE[0]))


if __name__ == "__main__": main()

download_scannetv2.py

#coding:utf-8
#!/usr/bin/env python
# Downloads ScanNet public data release
# Run with ./download-scannet.py (or python download-scannet.py on Windows)
# -*- coding: utf-8 -*-
import argparse
import os
import urllib.request      #(for python3)
# import urllib
import tempfile

BASE_URL = 'http://kaldir.vc.in.tum.de/scannet/'
TOS_URL = BASE_URL + 'ScanNet_TOS.pdf'
FILETYPES = ['.sens', '.txt',
             '_vh_clean.ply', '_vh_clean_2.ply',
             '_vh_clean.segs.json', '_vh_clean_2.0.010000.segs.json',
             '.aggregation.json', '_vh_clean.aggregation.json',
             '_vh_clean_2.labels.ply',
             '_2d-instance.zip', '_2d-instance-filt.zip',
             '_2d-label.zip', '_2d-label-filt.zip']
FILETYPES_TEST = ['.sens', '.txt', '_vh_clean.ply', '_vh_clean_2.ply']
PREPROCESSED_FRAMES_FILE = ['scannet_frames_25k.zip', '5.6GB']
TEST_FRAMES_FILE = ['scannet_frames_test.zip', '610MB']
LABEL_MAP_FILES = ['scannetv2-labels.combined.tsv', 'scannet-labels.combined.tsv']
RELEASES = ['v2/scans', 'v1/scans']
RELEASES_TASKS = ['v2/tasks', 'v1/tasks']
RELEASES_NAMES = ['v2', 'v1']
RELEASE = RELEASES[0]
RELEASE_TASKS = RELEASES_TASKS[0]
RELEASE_NAME = RELEASES_NAMES[0]
LABEL_MAP_FILE = LABEL_MAP_FILES[0]
RELEASE_SIZE = '1.2TB'
V1_IDX = 1


def get_release_scans(release_file):
    scan_lines = urllib.request.urlopen(release_file)
    # scan_lines = urllib.urlopen(release_file)
    scans = []
    for scan_line in scan_lines:
        scan_id = scan_line.decode('utf8').rstrip('\n')
        scans.append(scan_id)
    return scans


def download_release(release_scans, out_dir, file_types, use_v1_sens):
    if len(release_scans) == 0:
        return
    print('Downloading ScanNet ' + RELEASE_NAME + ' release to ' + out_dir + '...')
    for scan_id in release_scans:
        scan_out_dir = os.path.join(out_dir, scan_id)
        download_scan(scan_id, scan_out_dir, file_types, use_v1_sens)
    print('Downloaded ScanNet ' + RELEASE_NAME + ' release.')


def download_file(url, out_file):
    out_dir = os.path.dirname(out_file)
    if not os.path.isdir(out_dir):
        os.makedirs(out_dir)
    if not os.path.isfile(out_file):
        print('\t' + url + ' > ' + out_file)
        fh, out_file_tmp = tempfile.mkstemp(dir=out_dir)
        f = os.fdopen(fh, 'w')
        f.close()
        urllib.request.urlretrieve(url, out_file_tmp)
        # urllib.urlretrieve(url, out_file_tmp)
        os.rename(out_file_tmp, out_file)
    else:
        print('WARNING: skipping download of existing file ' + out_file)


def download_scan(scan_id, out_dir, file_types, use_v1_sens):
    print('Downloading ScanNet ' + RELEASE_NAME + ' scan ' + scan_id + ' ...')
    if not os.path.isdir(out_dir):
        os.makedirs(out_dir)
    for ft in file_types:
        v1_sens = use_v1_sens and ft == '.sens'
        url = BASE_URL + RELEASE + '/' + scan_id + '/' + scan_id + ft if not v1_sens else BASE_URL + RELEASES[
            V1_IDX] + '/' + scan_id + '/' + scan_id + ft
        out_file = out_dir + '/' + scan_id + ft
        download_file(url, out_file)
    print('Downloaded scan ' + scan_id)


def download_task_data(out_dir):
    print('Downloading ScanNet v1 task data...')
    files = [
        LABEL_MAP_FILES[V1_IDX], 'obj_classification/data.zip',
        'obj_classification/trained_models.zip', 'voxel_labeling/data.zip',
        'voxel_labeling/trained_models.zip'
    ]
    for file in files:
        url = BASE_URL + RELEASES_TASKS[V1_IDX] + '/' + file
        localpath = os.path.join(out_dir, file)
        localdir = os.path.dirname(localpath)
        if not os.path.isdir(localdir):
            os.makedirs(localdir)
        download_file(url, localpath)
    print('Downloaded task data.')


def download_label_map(out_dir):
    print('Downloading ScanNet ' + RELEASE_NAME + ' label mapping file...')
    files = [LABEL_MAP_FILE]
    for file in files:
        url = BASE_URL + RELEASE_TASKS + '/' + file
        localpath = os.path.join(out_dir, file)
        localdir = os.path.dirname(localpath)
        if not os.path.isdir(localdir):
            os.makedirs(localdir)
        download_file(url, localpath)
    print('Downloaded ScanNet ' + RELEASE_NAME + ' label mapping file.')


def main():
    parser = argparse.ArgumentParser(description='Downloads ScanNet public data release.')
    parser.add_argument('-o', '--out_dir', required=True, help='directory in which to download')
    parser.add_argument('--task_data', action='store_true', help='download task data (v1)')
    parser.add_argument('--label_map', action='store_true', help='download label map file')
    parser.add_argument('--v1', action='store_true', help='download ScanNet v1 instead of v2')
    parser.add_argument('--id', help='specific scan id to download')
    parser.add_argument('--preprocessed_frames', action='store_true',
                        help='download preprocessed subset of ScanNet frames (' + PREPROCESSED_FRAMES_FILE[1] + ')')
    parser.add_argument('--test_frames_2d', action='store_true', help='download 2D test frames (' + TEST_FRAMES_FILE[
        1] + '; also included with whole dataset download)')
    parser.add_argument('--type',
                        help='specific file type to download (.aggregation.json, .sens, .txt, _vh_clean.ply, _vh_clean_2.0.010000.segs.json, _vh_clean_2.ply, _vh_clean.segs.json, _vh_clean.aggregation.json, _vh_clean_2.labels.ply, _2d-instance.zip, _2d-instance-filt.zip, _2d-label.zip, _2d-label-filt.zip)')
    args = parser.parse_args()

    print(
        'By pressing any key to continue you confirm that you have agreed to the ScanNet terms of use as described at:')
    print(TOS_URL)
    print('***')
    print('Press any key to continue, or CTRL-C to exit.')
    key = input('')

    if args.v1:
        global RELEASE
        global RELEASE_TASKS
        global RELEASE_NAME
        global LABEL_MAP_FILE
        RELEASE = RELEASES[V1_IDX]
        RELEASE_TASKS = RELEASES_TASKS[V1_IDX]
        RELEASE_NAME = RELEASES_NAMES[V1_IDX]
        LABEL_MAP_FILE = LABEL_MAP_FILES[V1_IDX]

    release_file = BASE_URL + RELEASE + '.txt'  # 存放场景ID的文件
    release_scans = get_release_scans(release_file)  # 所有场景的ID
    file_types = FILETYPES;  # 所有文件的后缀名
    release_test_file = BASE_URL + RELEASE + '_test.txt'  # 存放测试场景ID的文件
    release_test_scans = get_release_scans(release_test_file)  # 测试场景的ID
    file_types_test = FILETYPES_TEST;  # 测试相关文件的后缀名
    out_dir_scans = os.path.join(args.out_dir, 'scans')  # 下载文件的子文件夹
    out_dir_test_scans = os.path.join(args.out_dir, 'scans_test')  # 下载文件的子文件夹
    out_dir_tasks = os.path.join(args.out_dir, 'tasks')  # 下载文件的子文件夹

    # 指定下载的文件类型
    if args.type:  # download file type
        file_type = args.type
        if file_type not in FILETYPES:
            print('ERROR: Invalid file type: ' + file_type)
            return
        file_types = [file_type]
        if file_type in FILETYPES_TEST:
            file_types_test = [file_type]
        else:
            file_types_test = []
    if args.task_data:  # download task data
        download_task_data(out_dir_tasks)
    elif args.label_map:  # download label map file
        download_label_map(args.out_dir)
    elif args.preprocessed_frames:  # download preprocessed scannet_frames_25k.zip file
        if args.v1:
            print('ERROR: Preprocessed frames only available for ScanNet v2')
        print('You are downloading the preprocessed subset of frames ' + PREPROCESSED_FRAMES_FILE[
            0] + ' which requires ' + PREPROCESSED_FRAMES_FILE[1] + ' of space.')
        download_file(os.path.join(BASE_URL, RELEASE_TASKS, PREPROCESSED_FRAMES_FILE[0]),
                      os.path.join(out_dir_tasks, PREPROCESSED_FRAMES_FILE[0]))
    elif args.test_frames_2d:  # download test scannet_frames_test.zip file
        if args.v1:
            print('ERROR: 2D test frames only available for ScanNet v2')
        print('You are downloading the 2D test set ' + TEST_FRAMES_FILE[0] + ' which requires ' + TEST_FRAMES_FILE[
            1] + ' of space.')
        download_file(os.path.join(BASE_URL, RELEASE_TASKS, TEST_FRAMES_FILE[0]),
                      os.path.join(out_dir_tasks, TEST_FRAMES_FILE[0]))
    elif args.id:  # download single scan
        scan_id = args.id
        is_test_scan = scan_id in release_test_scans
        if scan_id not in release_scans and (not is_test_scan or args.v1):
            print('ERROR: Invalid scan id: ' + scan_id)
        else:
            out_dir = os.path.join(out_dir_scans, scan_id) if not is_test_scan else os.path.join(out_dir_test_scans,
                                                                                                 scan_id)
            scan_file_types = file_types if not is_test_scan else file_types_test
            use_v1_sens = not is_test_scan
            if not is_test_scan and not args.v1 and '.sens' in scan_file_types:
                print(
                    'Note: ScanNet v2 uses the same .sens files as ScanNet v1: Press \'n\' to exclude downloading .sens files for each scan')
                key = input('')
                if key.strip().lower() == 'n':
                    scan_file_types.remove('.sens')
            download_scan(scan_id, out_dir, scan_file_types, use_v1_sens)
    else:  # download entire release
        if len(file_types) == len(FILETYPES):
            print(
                'WARNING: You are downloading the entire ScanNet ' + RELEASE_NAME + ' release which requires ' + RELEASE_SIZE + ' of space.')
        else:
            print('WARNING: You are downloading all ScanNet ' + RELEASE_NAME + ' scans of type ' + file_types[0])
        print(
            'Note that existing scan directories will be skipped. Delete partially downloaded directories to re-download.')
        print('***')
        print('Press any key to continue, or CTRL-C to exit.')
        key = input('')
        if not args.v1 and '.sens' in file_types:
            print(
                'Note: ScanNet v2 uses the same .sens files as ScanNet v1: Press \'n\' to exclude downloading .sens files for each scan')
            key = input('')
            if key.strip().lower() == 'n':
                file_types.remove('.sens')
        download_release(release_scans, out_dir_scans, file_types, use_v1_sens=True)
        if not args.v1:
            download_label_map(args.out_dir)
            download_release(release_test_scans, out_dir_test_scans, file_types_test, use_v1_sens=False)
            download_file(os.path.join(BASE_URL, RELEASE_TASKS, TEST_FRAMES_FILE[0]),
                          os.path.join(out_dir_tasks, TEST_FRAMES_FILE[0]))


if __name__ == "__main__": main()

The above two codes can be copied according to your own needs.
Start downloading the dataset

#-o 保存文件路径
python download_scannet.py -o data

Since the entire data is large, the author also provides the option scannet_frames_25k for a smaller subset.

#下载scannet_frames_25k
python download-scannet.py -o data --preprocessed_frames 

You can choose to download the two codes according to your actual needs. (The author here downloads all of them)
Pay attention to the python environment.

If the download speed is very slow, you can also copy the URL provided below into the browser to download, which will make it faster.

3. Export the data set

Since the downloaded file is in .sens format, the data needs to be further exported. Officially provided export code: https://github.com/ScanNet/ScanNet/tree/master/SensReader/python
File directory

to start exporting

python reader.py --filename scene0000_00.sens --output_path image 

1. Note : Set the required exported files from False to True

2. In order to view the export process more intuitively, here is a reference to the RGB-D data set: ScanNet
modified part of the SensorData.py code

from tqdm import tqdm 
#更换71行代码：for i in range(num_frames): 为：
for i in tqdm(range(num_frames),ncols=80):
#相应的81行、93行 也可以相应更换为：
for f in tqdm(range(0, len(self.frames), frame_skip),ncols=80):
for f in tqdm(range(0, len(self.frames), frame_skip),ncols=80):

File directory after export

Reference blog
RGB-D dataset: ScanNet
About ScanNet dataset