chordatlas - GitLite

KO | EN

gitlite — search

#python #hacktoberfest #typescript #llm #go #android #machine-learning #deep-learning #kubernetes #awesome-list #vue #pytorch #mcp #open-source

chordatlas

(★ 117)

data driven urban procedural modeling

파일 탐색기

최종 버전 다운로드 (.zip)

- - bug_report.md
  - feature_request.md
- org.eclipse.core.resources.prefs
- org.eclipse.jdt.core.prefs
- org.eclipse.m2e.core.prefs
- build.sh
- Dockerfile
- update_and_export.sh
- pic.jpg
.classpath
.gitignore
.project
LICENSE
pom.xml
README.md

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/twak/chordatlas

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd chordatlas

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Docker

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Docker Desktop 컨테이너를 빌드하고 실행하려면 필요합니다. 설치 후 실행해서 백그라운드에 켜두세요.

docker build -f build/Dockerfile -t chordatlas .

Dockerfile을 기반으로 실행 가능한 이미지를 빌드합니다.

docker run -p 8080:80 chordatlas

빌드된 이미지를 실제 컨테이너로 실행합니다.

✅ 터미널에 docker compose ps 를 입력해 컨테이너들이 Up 상태인지 확인하세요. README에 포트 번호가 적혀있다면 브라우저에서 http://localhost:포트번호 로 접속해보세요.

3. Maven (Java)

보통

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
JDK (Java) Java 프로젝트를 빌드/실행하려면 필요합니다.
Maven mvn 명령어를 쓰기 위한 빌드 도구입니다.

mvn clean install

Maven으로 의존성 설치와 빌드를 진행합니다.

✅ BUILD SUCCESS 메시지가 뜨면 성공입니다. target/ 폴더에 결과물이 생성됩니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# chordatlas: data-driven urban procedural modeling
[![](https://jitpack.io/v/twak/chordatlas.svg)](https://jitpack.io/#twak/chordatlas)

chordatlas is an urban procedural modeling and data fusion research platform. [UI video](https://youtu.be/Jz8q09r-RFg). It contains implementations of 3 projects that have be presented at various Siggraphs: [frankengan](http://geometry.cs.ucl.ac.uk/projects/2018/frankengan/), [bigsur](http://geometry.cs.ucl.ac.uk/projects/2017/bigsur/), and [procex](https://twak.org/project/procex/).

procex ([video](https://youtu.be/K0yUXjM_YKE)) are a mathematical model of traditional buildings, bigsur ([london video](https://youtu.be/HW7WR7ZywJc)) fits these to real world data, and frankengan ([madrid video](https://www.youtube.com/watch?v=78N-wfCiCuc)) textures them.

![interface pic which melts your eyes](https://raw.githubusercontent.com/twak/chordatlas/22b4513bb2e1ac8c9bc1034c4b187025346f5d1a/wiki/pic.jpg)

## run

the system is developed on ubuntu, but most of the non-machine learning systems should work on any platform. chordatlas is very much "academic-grade" - if you have problems using this system, I would love to [know](https://github.com/twak/chordatlas/issues) so I can fix them!

1. install [java 8+](http://www.oracle.com/technetwork/java/javase/downloads/index.html)
1. download the [chordatlas binary](https://drive.google.com/open?id=1FC5K2kKP12jQLlE97YlwhzceTrLgxuDn)
1. run with `java -Dsun.java2d.uiScale=1 -jar -Xmx10g chordatlas-0.0.1-SNAPSHOT.jar`  (code is academic grade: use at your own risk. the 10g says to use a 10Gb heap)
1. read the [user interface instructions](https://github.com/twak/chordatlas/wiki/interface-instructions-and-pipeline-videos) or [watch the ui video](https://youtu.be/Jz8q09r-RFg).

there are additional requirements and instructions for [bigsur](https://github.com/twak/chordatlas/wiki/bigSUR-details) (creates clean meshes from noisy meshes, streetview info, and maps) and [frankengan](https://github.com/twak/chordatlas/wiki/frankenGAN-details) (textures the meshes, generates feature locations).

more adventurous hackers may be interested in compiling their [own datasets](https://github.com/twak/chordatlas/wiki/datasets) or [building the system](https://github.com/twak/chordatlas/wiki/build-instructions).

## plugins

plugins for chordatlas/tweed (mostly under development; my goal is to split out the tweed GUI/engine from applications):

1. streets ([stub](https://github.com/twak/tweedstreets), [impl](https://github.com/Jhilik3/tweedstreets))
1. floorplans ([tba](https://github.com/twak/planchordatlas))

## cite

if you use this project in your own publications, please cite the appropriate paper(s). this helps us get more funding to improve the systems:

```
@article{frankengan,
  title = {FrankenGAN: Guided Detail Synthesis for Building Mass-Models Using Style-Synchonized GANs},
  author = {Tom Kelly and Paul Guerrero and Anthony Steed and Peter Wonka and Niloy J. Mitra},
  year = {2018},
  journal = {{ACM} Transactions on Graphics},
  volume = {37},
  number = {6},
  doi = {10.1145/3272127.3275065},
}
```

```
@article{bigsur,
  title   = {BigSUR: Large-scale Structured Urban Reconstruction},
  author  = {Tom Kelly and John Femiani and Peter Wonka and Niloy J. Mitra},
  year    = {2017},
  journal = {{ACM} Transactions on Graphics},
  volume = {36},
  number = {6},
  doi = {10.1145/3130800.3130823}
}
```

```
@article{procex,
 title = {Interactive Architectural Modeling with Procedural Extrusions},
 author = {Tom Kelly and Peter Wonka},
 year = {2011},
 journal = {{ACM} Transactions on Graphics},
 volume = {30},
 number = {2},
 doi = {10.1145/1944846.1944854},
}
```