Cloud2BIM - GitLite

KO | EN

gitlite — search

#hacktoberfest #react #llm #golang #android #machine-learning #rust #linux #java #windows #awesome #cli #awesome-list #openai

Cloud2BIM

(★ 130)

Codes for automatic point-cloud-to-BIM conversion

파일 탐색기

최종 버전 다운로드 (.zip)

- - class_balance.png
  - class_legend.png
  - confusion_matrix.png
  - epoch_metrics.png
  - grid_sensitivity.png
  - lr_schedules.png
  - p1_perclass_delta.png
  - probe_ablation.png
  - qualitative_synth_pred.png
  - real_scan_a623_pred.png
  - training_lineage.png
  - training_progress.png
- README.md
- - .gitignore
- .gitignore
- .gitignore
- .gitignore
- .gitignore
.gitattributes
.gitignore
aux_functions.py
cloud2entities.py
config.yaml
generate_ifc.py
LICENSE
plotting_functions.py
README.md
requirements.txt
space_generator.py
title.png

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/VaclavNezerka/Cloud2BIM

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd Cloud2BIM

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Python

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

pip install -r requirements.txt

requirements.txt 등에 명시된 파이썬 라이브러리를 설치합니다.

python <실행할 파일명>.py # README에서 정확한 실행 파일명을 확인하세요

파이썬 스크립트(또는 모듈)를 실행합니다.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Cloud2BIM
![Workflow](https://raw.githubusercontent.com/VaclavNezerka/Cloud2BIM/master/title.png)

# Project Update & Advanced Version:
> This repository contains the foundational open-source research version of the Cloud2BIM algorithm. An advanced, production-ready version of this software, **Cloud2BIM-AI**, is now available through **Constriq** (a Czech Technical University spin-off). 
>
> While the open-source script provides core functionality, **Cloud2BIM-AI** is actively developed for commercial and enterprise workflows, offering the following expanded capabilities:
> * **Enhanced Element Recognition:** Advanced AI models capable of recognizing a wider variety of complex building elements with higher precision.
> * **Increased Robustness:** Fully automated processing that eliminates the need for manual parameter tuning.
> * **Optimized Performance:** Significantly reduced computational time for large-scale point cloud datasets.
> * **Continuous Support & GUI:** A user-friendly interface with visual verification and ongoing technical development.
>
> For professional deployment and access to the advanced version, please visit: **[constriq.tech](https://constriq.tech/)**

---

### Description
Cloud2BIM automates the Scan-to-BIM process by converting point clouds into 3D parametric entities. It employs a segmentation algorithm that utilizes point cloud density analysis, augmented by image and morphological operations. This allows the software to precisely extract the geometry of building elements such as slabs, walls, windows, and doors.

### Installation
To install Cloud2BIM, follow these steps:
git clone

https://github.com/VaclavNezerka/Cloud2BIM.git

Install dependencies:

First, ensure you have Python and pip installed.
Then, install the required dependencies listed in the requirements.txt file:

pip install -r requirements.txt

# Running the Script
The `cloud2entities.py` script requires a YAML configuration file to run. You can provide the path to the 
configuration file as a command-line argument. If no argument is provided, the script will 
automatically use the default file `config.yaml`.

### Example command

python cloud2entities.py config.yaml

### Dataset
The complete original point cloud for Kladno station is available at Zenodo platform.

https://zenodo.org/records/14221915

## Citation

If you find this project or any part of it useful in your research or work, please consider citing the following article:

@article{Cloud2BIM_2025,
    title = {Open-source automatic pipeline for efficient conversion of large-scale point clouds to IFC format},
    journal = {Automation in Construction},
    volume = {177},
    pages = {106303},
    year = {2025},
    issn = {0926-5805},
    doi = {https://doi.org/10.1016/j.autcon.2025.106303},
    author = {Slávek Zbirovský and Václav Nežerka},
}

# License
MIT License