This repository provides a basic implementation of the non-rigid point cloud registration method described in [1]. For a detailed explanation of the method and its motivation, please refer to the original paper. In a nutshell, the method is able to find the set of rigid transformations that need to be applied to each line in the scan in order to match an existing model:

You can also watch the video that summarizes this work:

Additionally, you can watch the presentation of this work at IROS 2022:

Thank you for citing the original publication [1] if you use our method in academic work:

@ARTICLE{9788023,  
  author={Castillón, Miguel and Ridao, Pere and Siegwart, Roland and Cadena, César},
  journal={IEEE Robotics and Automation Letters},
  title={Linewise Non-Rigid Point Cloud Registration},
  year={2022},
  volume={7},
  number={3},
  pages={7044-7051},
  doi={10.1109/LRA.2022.3180038}}

If you want to know more about our underwater 3D scanner, check out the paper [2] and this blog post.

[1] M. Castillón, P. Ridao, R. Siegwart and C. Cadena, "Linewise Non-Rigid Point Cloud Registration," in IEEE Robotics and Automation Letters, doi: 10.1109/LRA.2022.3180038. [pdf]

[2] M. Castillón, J. Forest and P. Ridao, "Underwater 3D Scanner to Counteract Refraction: Calibration and Experimental Results," in IEEE/ASME Transactions on Mechatronics, doi: 10.1109/TMECH.2022.3170504. [pdf]

Our methods depends on CMake, Eigen, PCL and Ceres [please note that so far, it has only been tested on Ubuntu 20.04 + Eigen 3.3.7 + PCL 1.10 + Ceres 2.2.] Moreover, our method uses Fast Gauss Transforms to compute the correspondence probability between each pair of points. Therefore, our method depends on fgt, which is a fork of this repository.

In summary, first do:

sudo apt install \
    cmake \
    libeigen3-dev \
    libpcl-dev

Then, in your libraries folder, compile Ceres:

git clone https://ceres-solver.googlesource.com/ceres-solver
cd ceres-solver && mkdir build && cd build
cmake .. \
    -DBUILD_TESTING=OFF \
    -DBUILD_EXAMPLES=OFF
make -jX 
sudo make install
cd ../..

Then compile fgt:

git clone https://github.com/miguelcastillon/fgt_threshold
cd fgt_threshold && mkdir build && cd build
cmake .. \
    -DCMAKE_BUILD_TYPE=Release \
    -DWITH_OPENMP=ON \
    -DBUILD_SHARED_LIBS=ON \
    -DWITH_TESTS=OFF
make -jX 
sudo make install
cd ../..

As usual, just download and unzip this repository in your preferred location and cd into it. Then:

git clone https://github.com/miguelcastillon/lnrr
cd lnrr && mkdir build && cd build
cmake [OPTIONS] .. 
make -jX 
sudo make install

There are several options that you can pass to CMake:

• -DCMAKE_BUILD_TYPE=Debug to get information for each iteration (default is Release).
• -DBUILD_TESTS=OFF to disable the compilation of the tests (default is ON).

If at any point you want to uninstall the library, just do:

sudo make uninstall

#include <lnrr/scan_to_model.h>

int main(int argc, char** argv) {
    lnrr::PointCloudPtr fixed = loadModel();
    std::vector<lnrr::PointCloudPtr> moving = loadScan();
    double beta = ...;
    double lambda = ...;

    lnrr::ScanToModel lnrr(fixed, moving, beta, lambda);
    lnrr::Result result = lnrr.run();
    return 0;
}

And your CMakeLists.txt should include:

find_package(OpenMP REQUIRED)
find_package(Ceres REQUIRED)
find_package(Fgt REQUIRED)
find_package(Lnrr REQUIRED)

add_library(my-new-library
    my_program.cpp
    )
target_link_libraries(my-new-library
    PUBLIC
    Lnrr::Library-C++
    )

Check the folder examples to see how to write a .cpp file and a CMakeLists.txt for your project.

There is an example in the examples folder. Inside, you can run

mkdir build 
cd build 
cmake .. 
make -jX

Then, from examples/build you can run it like this:

./lnrr_example \
    ../data/model.pcd \
    ../data/scans/ \
    ../data/output.pcd \
    5 \
    30000 \
    0.03

Please feel free to create issues and pull requests, they will be much appreciated.

Please be aware that this repository is only a simple implementation of the method and may therefore unfortunately not always show a robust behaviour. There is no documentation yet but we hope the code is self-explanatory.

This library is GPL2, copyright 2022 Miguel Castillón. See LICENSE.txt for the full license text.

In the creation of this library we have drawn inspiration from this cpd implementation by Gadomski.