scannet v2 data set download (WP)

scannet data set:
A total of 1513 collection scene data (the number of point clouds in each scene is different. If you want to use end-to-end, you may need to sample, so that each The points of the scene are all the same), a total of 21 categories of objects, of which 1201 scenes are used for training and 312 scenes are used for testing. There are four evaluation tasks: 3D semantic segmentation, 3D instance segmentation, 2D semantic segmentation and 2D instances. segmentation.

There will be a network disk link at the end of this article.

If you go to the official website to download, you need to fill in a TOS agreement, and then send an email to it, and you will get a python script.
Similar to the following, the script is saved in github.

#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

### 剩下的就不贴了，你懂得

The entire data size is 1.2T, which is too large. Only the required part is downloaded.

python3 download-scannetv2.py -o scannet/ --type  _vh_clean_2.ply
python3 download-scannetv2.py -o scannet/ --type  _vh_clean_2.labels.ply
python3 download-scannetv2.py -o scannet/ --type  _vh_clean_2.0.010000.segs.json
python3 download-scannetv2.py -o scannet/ --type  .aggregation.json

After downloading, it will look like this, included in the network disk file.

Insert image description here
Show one of them

>>> import open3d as o3d
>>> pcd = o3d.io.read_point_cloud('scene0000_00_vh_clean_2.ply')
>>> o3d.visualization.draw_geometries([pcd])

Insert image description here
Take a look at its semantic tags

>>> pcd = o3d.io.read_point_cloud('scene0000_00_vh_clean_2.labels.ply')
>>> o3d.visualization.draw_geometries([pcd])

Insert image description here

Connection:Location
Transfer: roq0

scannet v2 data set download (WP)

Guess you like