Open3D: A Modern Library for 3D Data Processing (Paddle backend)

Important

This branch(paddle) experimentally integrates Paddle backend to Open3D meachine learning module.

It was developed base version v0.18.0 of Open3D. It is recommended to install nightly-build(develop) Paddle before running any code in this branch.

It was verified on Ubuntu 20.04. It may meet some problems if you are using other environment.

Build and Install

# replace gcc, g++ with 9.4.0 version(important, or you may meet some problems when make install-pip-package)
rm /usr/bin/gcc /usr/bin/g++
mv /usr/bin/gcc.bak /usr/bin/gcc
mv /usr/bin/g++.bak /usr/bin/g++

# install dependencies
cd Open3D
bash util/install_deps_ubuntu.sh
pip install wheel yapf==0.30.0

# install cmake 3.23(optional, if you have installed cmake 3.23 or higher version, please skip this step)
wget -nc https://paddle-org.bj.bcebos.com/paddlescience/cmake-3.23.0-linux-x86_64.tar.gz
tar -zxvf cmake-3.23.0-linux-x86_64.tar.gz
rm -f cmake-3.23.0-linux-x86_64.tar.gz
PATH=$PWD/cmake-3.23.0-linux-x86_64/bin:$PATH

# install nightly-build paddlepaddle-gpu
pip uninstall paddlepaddle-gpu
pip install --pre paddlepaddle-gpu -i https://www.paddlepaddle.org.cn/packages/nightly/cu118/

# configure
mkdir build
cd build
cmake  -DBUILD_CUDA_MODULE=ON \
       -DBUILD_PADDLE_OPS=ON  \
       -DGLIBCXX_USE_CXX11_ABI=ON \
       -DBUNDLE_OPEN3D_ML=OFF \
       ..

# install
make install-pip-package -j8

Open3D for paddle backend also provide Dockerfile to help build from docker. More details please refer to the document.

Unit Test

Please make sure you have installed Open3D for paddle backend correctly before running unit tests

util/run_python_unittest.sh

Below is Open3D's original README

Homepage | Docs | Quick Start | Compile | Python | C++ | Open3D-ML | Viewer | Contribute | Demo | Forum

Open3D is an open-source library that supports rapid development of software that deals with 3D data. The Open3D frontend exposes a set of carefully selected data structures and algorithms in both C++ and Python. The backend is highly optimized and is set up for parallelization. We welcome contributions from the open-source community.

Core features of Open3D include:

• 3D data structures
• 3D data processing algorithms
• Scene reconstruction
• Surface alignment
• 3D visualization
• Physically based rendering (PBR)
• 3D machine learning support with PyTorch and TensorFlow
• GPU acceleration for core 3D operations
• Available in C++ and Python

Here's a brief overview of the different components of Open3D and how they fit together to enable full end to end pipelines:

For more, please visit the Open3D documentation.

Python quick start

Pre-built pip packages support Ubuntu 18.04+, macOS 10.15+ and Windows 10+ (64-bit) with Python 3.8-3.11.

# Install
pip install open3d       # or
pip install open3d-cpu   # Smaller CPU only wheel on x86_64 Linux (v0.17+)

# Verify installation
python -c "import open3d as o3d; print(o3d.__version__)"

# Python API
python -c "import open3d as o3d; \
           mesh = o3d.geometry.TriangleMesh.create_sphere(); \
           mesh.compute_vertex_normals(); \
           o3d.visualization.draw(mesh, raw_mode=True)"

# Open3D CLI
open3d example visualization/draw

To get the latest features in Open3D, install the development pip package. To compile Open3D from source, refer to compiling from source.

C++ quick start

Checkout the following links to get started with Open3D C++ API

• Download Open3D binary package: Release or latest development version
• Compiling Open3D from source
• Open3D C++ API

To use Open3D in your C++ project, checkout the following examples

• Find Pre-Installed Open3D Package in CMake
• Use Open3D as a CMake External Project

Open3D-Viewer app

Open3D-Viewer is a standalone 3D viewer app available on Debian (Ubuntu), macOS and Windows. Download Open3D Viewer from the release page.

Open3D-ML

Open3D-ML is an extension of Open3D for 3D machine learning tasks. It builds on top of the Open3D core library and extends it with machine learning tools for 3D data processing. To try it out, install Open3D with PyTorch or TensorFlow and check out Open3D-ML.

Communication channels

• GitHub Issue: bug reports, feature requests, etc.
• Forum: discussion on the usage of Open3D.
• Discord Chat: online chats, discussions, and collaboration with other users and developers.

Citation

Please cite our work if you use Open3D.

@article{Zhou2018,
    author    = {Qian-Yi Zhou and Jaesik Park and Vladlen Koltun},
    title     = {{Open3D}: {A} Modern Library for {3D} Data Processing},
    journal   = {arXiv:1801.09847},
    year      = {2018},
}