Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/CKchaos/scn2pointcloud_tool
The toolbox implements the data conversion from CAD models (such as .obj/.off file) to point cloud(surface voxels) with RGB value and labels.
https://github.com/CKchaos/scn2pointcloud_tool
c-plus-plus cad-models point-cloud pointcloud python
Last synced: about 2 months ago
JSON representation
The toolbox implements the data conversion from CAD models (such as .obj/.off file) to point cloud(surface voxels) with RGB value and labels.
- Host: GitHub
- URL: https://github.com/CKchaos/scn2pointcloud_tool
- Owner: CKchaos
- Created: 2017-03-11T05:06:07.000Z (almost 8 years ago)
- Default Branch: master
- Last Pushed: 2018-07-25T15:03:31.000Z (over 6 years ago)
- Last Synced: 2024-08-01T03:29:11.310Z (5 months ago)
- Topics: c-plus-plus, cad-models, point-cloud, pointcloud, python
- Language: C++
- Homepage:
- Size: 17.7 MB
- Stars: 64
- Watchers: 9
- Forks: 16
- Open Issues: 0
-
Metadata Files:
- Readme: ReadMe.md
Awesome Lists containing this project
README
# scn2pointcloud_tool Documentation
The aim of this tool is to achieve data conversion from the format of CAD models, such as .obj/.off file, to the format of **point cloud with RGB and labels**. The convert result of this tool is as follows.
The visualization of an OBJ file:
The visualization of its corresponding output:
The tool is designed for SUNCG dataset and based on the data organization of SUNCG dataset, so, for other dataset of CAD models, the tool may be not compatible completely. You can see this [webpage](http://suncg.cs.princeton.edu) and [paper](https://arxiv.org/pdf/1611.08974v1.pdf) for more details about SUNCG dataset.
The tool is modified from [SUNCGtoolbox](https://github.com/shurans/SUNCGtoolbox), which is modified from GAPS. The original GAPS README is on the bottom.
### Bibtex
If you find this tool useful in your research, please consider citing our [paper](http://arxiv.org/abs/1707.06783) .
```
@InProceedings{Liu_2017_ICCV,
author = {Liu, Fangyu and Li, Shuaipeng and Zhang, Liqiang and Zhou, Chenghu and Ye, Rongtian and Wang, Yuebin and Lu, Jiwen},
title = {3DCNN-DQN-RNN: A Deep Reinforcement Learning Framework for Semantic Parsing of Large-Scale 3D Point Clouds},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}
```
### Tool Organization
```
data_func
|-- demo.py - display how to implement the conversion
|-- data_module.py - build a link between libdata.so and python function
|-- libdata.so - Dynamic Link Library produced by g++
SUNCGtoolbox
|--gaps
|-- pkgs - source and include files for all packages (software libraries)
|-- apps
|--scn2pointcloud - program that implements the conversion algorithm
|-- makefiles - unix-style make file definitions
|-- vc - visual studio solution files
|-- lib - archive library (.lib) files (created during compilation)
|-- bin - executable files (created during compilation)
|--metadata
```
**Note**: The organization of SUNCGtoolbox in this repository is almost same as [SUNCGtoolbox](https://github.com/shurans/SUNCGtoolbox). A number of class files are modified to achieve the aim of data conversion.
### Usage
##### Compilation
```cmake
cd SUNCGtoolbox/gaps
make clean
make
```
##### Generate Dynamic Link Library
```cmake
cd SUNCGtoolbox/gaps/apps/scn2pointcloud/
g++ -shared -fPIC -o libdata.so scn2pointcloud.cpp -L../../lib/x86_64 -g -lR3Graphics -lR3Shapes -lR2Shapes -lRNBasics -ljpeg -lpng -lfglut -lGLU -lGL -lX11 -lm -I. -I../../pkgs -g
```
If nothing is wrong, you will get a file named libdata.so, the method to use this file is described in data_func.
### GAPS README
GAPS Users -
This directory contains all code for the GAPS software library.
There are several subdirectories:
pkgs - source and include files for all packages (software libraries).
apps - source files for several application and example programs.
makefiles - unix-style make file definitions
vc - visual studio solution files
lib - archive library (.lib) files (created during compilation).
bin - executable files (created during compilation).
If you are using linux or cygwin and have gcc and OpenGL development
libraries installed, or if you are using MAC OS X with the xcode
development environment, you should be able to compile all the code by
typing "make clean; make" in this directory. If you are using Windows
Visual Studio 10 or later, then you should be able to open the
solution file vc.sln in the vc subdirectory and then "Rebuild
Solution." For other development platforms, you should edit the shared
compilation settings in the makefiles/Makefiles.std to meet your needs.
To write a program that uses the GAPS pkgs, then you should include
"-I XXX/gaps/pkgs" in your compile flags (CFLAGS) and "-L
XXX/gaps/lib" in your link flags (LDFLAGS), where XXX is the directory
where you installed the gaps software.
The software is distributed under the MIT license (see LICENSE.txt)
and thus can be used for any purpose without warranty, any liability,
or any suport of any kind.
- [Tom Funkhouser](http://www.cs.princeton.edu/%7Efunk/)