Skip to content

mati3230/OpenXtract

Repository files navigation

OpenXtract

Reconstructed mesh of a living room scene. Reconstructed mesh of a living room scene.

Partition of the Cut-Pursuit algorithm. Partition of the Cut-Pursuit algorithm.

OpenXtract is a Blender add-on that allows to extract the object of interest by applying partition algorithms. Furthermore, one can also use the PointNet++ semantic segmentation. A short demonstration can be seen on YouTube, and a quickstart video is also available.

Downloads

We offer OpenXtract in combination with Blender, where one only must download the program to try OpenXtract. After the download, makse sure that OpenXtract is enabled as add-on. Click on Edit->Preferences, Add-Ons and search for OpenXtract. Activate the checkbox if it is disabled.

Windows

Linux

MacOs

  • Coming Soon.

Manual Installation with Miniconda

  1. Install miniconda and create an environment with a python version that matches your blender python interpreter.
  2. Install the dependencies with pip:
pip install -r requirements.txt
  1. Optional: Install PyTorch to enable the semantic segmentation functionality. Thanks to yanx27 et al. for creating and maintaining the PointNet++ repository
  2. Compile the partition algorithms in https://github.com/mati3230/3DPartitionAlgorithms and copy the resulting dynamic libraries into this project.
  3. Zip this folder (not only the contents).
  4. Import the add-on in blender by importing the zip file.

Citation

@inproceedings{Tiator2022,
   author = {Marcel Tiator and Calvin Huhn and Christian Geiger and Paul Grimm},
   city = {Virtual Event},
   journal = {Proceedings of the 5th International Conference on Artificial Intelligence and Virtual Reality - AIVR '22},
   publisher = {IEEE},
   title = {OpenXtract: A Blender Add-On for the Accelerated Extraction of the Objects of Interest},
   year = {2022},
}

Acknowledgements

This project is sponsored by: German Federal Ministry of Education and Research (BMBF) under the project number 13FH022IX6. Project name: Interactive body-near production technology 4.0 (German: Interaktive körpernahe Produktionstechnik 4.0 (iKPT4.0))

bmbf

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages