Comments (3)
There are two versions of the dataset: Original and aligned.
Aligned refers to the version where all of the rooms are rotated to be aligned with the canonical coordinate system.
Here what official readme says:
For those who want to use the globally aligned* point cloud versions directly, there exists a folder named "Aligned_Version", which contains the exact data as above (original version), but rotated according to the global alignment angles provided. Please note that the aligned version is only rotated; neither translated nor normalized.
...
*aligned = corresponds to the alignment that takes place before the element parsing (see in paper Section 3.2. Canonical Coordinate System Among Spaces)
So instead of rotating Aligned version you could just download the original dataset, which is what you show in the picture by default.
Here you can fill out the official form and have access to the both versions and the documentation:
https://docs.google.com/forms/d/e/1FAIpQLScDimvNMCGhy_rmBA2gHfDu3naktRm6A8BPwAWWDv-Uhm6Shw/viewform?c=0&w=1
The access to the dataset is instant once you have submitted the form.
from pointnet.
Hi @aborovac
Could you point where it is misaligned?
actually the data is processed by other PhD students in Prof. Saverese's lab:
http://cvgl.stanford.edu/index.html
from pointnet.
To fix misalignment I applied different rotations to some of the pointclouds. Below is the list of pointclouds and corresponding degrees to be applied (rotate around center point of point cloud)
Area6:
["office_11"]=90
["office_12"]=180
["office_13"]=180
["office_15"]=180
["office_16"]=180
["office_19"]=180
["office_22"]=180
["office_23"]=180
["office_24"]=180
["office_25"]=180
["office_26"]=180
["office_27"]=180
["office_28"]=180
["office_29"]=180
["office_31"]=90
["office_30"]=180
["office_33"]=180
["office_34"]=180
["office_35"]=180
["office_36"]=180
["office_37"]=180
["pantry_1"]=180
["hallway_1"]=-90
["hallway_2"]=90
from pointnet.
Related Issues (20)
- TypeError: float() argument must be a string or a number, not 'mpc'
- from tensorflow_graphics.util import export_api ImportError: No module named tensorflow_graphics.util Can someone help me to revolve this issue ?
- Add neuron to the ouput layer HOT 1
- s3dis dataset :ValueError: need at least one array to concatenate
- Unable to open H5py file HOT 3
- prepare dataset from h5 files with classification label per point
- meshlab
- PointNet for angle regression
- Area_5/hallway_6 HOT 1
- Issued certificate has expired HOT 1
- Annotation HOT 1
- A lightweight Cylinder3D model with much higher performance is now available!!!
- Isn't this section incorrect? HOT 1
- __init__() missing 1 required positional argument: 'dtype'
- How much memory needed for sem_seg training HOT 2
- How to visualize the semantic segmentation results through ROS
- how to use PointNet model in live inference HOT 1
- cant download dataset with HDF5 data. Help! HOT 1
- Segment point clouds with different point numbers
- Cannot get modelnet40 from server HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from pointnet.