## Introduction
Blendify is a lightweight Python framework that provides a high-level API for creating and rendering scenes with Blender. Developed with a focus on 3D computer vision visualization, Blendify simplifies access to selected Blender functions and objects.
Key features of Blendify:
1. **Simple interface:** Blendify provides a user-friendly interface for performing common visualization tasks without having to dive into the complicated Blender API.
2. **Easy integration:** Blendify seamlessly integrates with development scripts, implementing
commonly used routines and functions:
* native support of point clouds, meshes, and primitives;
* support of per-vertex colors and textures;
* advanced shadows with shadow catcher objects;
* video rendering with smooth camera trajectories;
* support for common camera models;
* import and export of .blend files for deeper integration with Blender;
* per-face definition of materials for meshes;
* support for common rotation representations and look-at utility to automatically setup orientation.
3. **Quick start:** Blendify is easy to get started with and does not require a standalone Blender installation. All you need to do is run `pip install blendify`.
4. **Blendify works in Colab:** check out [our Google Colab demo](https://colab.research.google.com/github/ptrvilya/blendify/blob/main/examples/ipynb/blendify_colab_demo.ipynb)!
## Installation instructions
### Install from pip
```bash
pip install blendify
```
### Optional requirements
```bash
pip install blendify[utils / examples / docs / all]
```
Running examples 4 and 5 requires [PyTorch](https://pytorch.org/) with [PyTorch3D](https://github.com/facebookresearch/pytorch3d/blob/main/INSTALL.md).
Running example 5 requires SMPL model files, please refer to the installation instructions in
[README](https://github.com/vchoutas/smplx#downloading-the-model).
## Quick Start
```python
# Script to render cube
from blendify import scene
from blendify.materials import PrincipledBSDFMaterial
from blendify.colors import UniformColors
# Add light
scene.lights.add_point(strength=1000, translation=(4, -2, 4))
# Add camera
scene.set_perspective_camera((512, 512), fov_x=0.7, rotation=(0.82, 0.42, 0.18, 0.34), translation=(5, -5, 5))
# Create material
material = PrincipledBSDFMaterial()
# Create color
color = UniformColors((0.0, 1.0, 0.0))
# Add cube mesh
scene.renderables.add_cube_mesh(1.0, material, color)
# Render scene
scene.render(filepath="cube.png")
```
## Feature walkthrough
Walkthrough of Blendify features with code and commentaries can be found [here](https://virtualhumans.mpi-inf.mpg.de/blendify/walkthrough.html).
## Examples
Check examples in our repository [here](https://github.com/ptrvilya/blendify#Examples).
## Changelog
The most recent version of Blendify is **2.0.0**. The update introduced some breaking changes that are
summarized alongside the overview of the new features in the [CHANGELOG](https://github.com/ptrvilya/blendify/blob/main/CHANGELOG.md) file.
## Citation
If you use Blendify in your research, please cite:
```bibtex
@article{blendify2024,
title={Blendify -- Python rendering framework for Blender},
author={Guzov, Vladimir and Petrov, Ilya A and Pons-Moll, Gerard},
journal={arXiv preprint arXiv:2410.17858},
year={2024}
}
```
## Works that use Blendify
* V. Lazova, E. Insafutdinov, G. Pons-Moll: [360-Degree Textures of People in Clothing from a Single Image](https://virtualhumans.mpi-inf.mpg.de/360tex/)
in 3DV'19
* B.L. Bhatnagar, X. Xie, **I. Petrov**, C. Sminchisescu, C. Theobalt, G. Pons-Moll:
[BEHAVE: Dataset and Method for Tracking Human Object Interactions](https://virtualhumans.mpi-inf.mpg.de/behave/), in CVPR'22
* X. Zhang, B.L. Bhatnagar, **V. Guzov**, S. Starke, G. Pons-Moll:
[COUCH: Towards Controllable Human-Chair Interactions](https://virtualhumans.mpi-inf.mpg.de/couch/), in ECCV'22
* G. Tiwari, D. Antic, J. E. Lenssen, N. Sarafianos, T. Tung, G. Pons-Moll: [Pose-NDF:
Modeling Human Pose Manifolds with Neural Distance Fields](https://virtualhumans.mpi-inf.mpg.de/posendf/), in ECCV'22
* **I. Petrov**, R. Marin, J. Chibane, G. Pons-Moll: [Object pop-up: Can we infer 3D objects and their poses from human interactions alone?](https://virtualhumans.mpi-inf.mpg.de/object_popup/), in CVPR'23
## Contributors
Blendify is written and maintained by [Vladimir Guzov](https://github.com/vguzov) and [Ilya Petrov](https://github.com/ptrvilya).
## Acknowledgments
We thank Verica Lazova for providing her Blender rendering scripts,
[István Sarandi](https://github.com/isarandi) for his suggestions and help in implementing new features,
and [Riccardo Marin](https://github.com/riccardomarin) for his helpful suggestions and feedback.
Our code for processing point clouds is mostly based on the amazing [Blender-Photogrammetry-Importer][BPI] addon.
## License
The code is released under the [GNU General Public License v3][GNU GPL v3].
The Python logo is trademark of Python Software Foundation.
The Blender logo is a registered property of Blender Foundation.
[Blender-Photogrammetry-Importer][BPI] is distributed under the [MIT License][BPI license].
Blender is released under the [GNU General Public License v3][GNU GPL v3].
[GNU GPL v3]: https://www.gnu.org/licenses/gpl-3.0.html
[BPI]: https://github.com/SBCV/Blender-Addon-Photogrammetry-Importer
[BPI license]: https://github.com/SBCV/Blender-Addon-Photogrammetry-Importer/blob/master/README.md
Raw data
{
"_id": null,
"home_page": "https://github.com/ptrvilya/blendify",
"name": "blendify",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": "rendering, pointcloud, blender, mesh",
"author": "Vladimir Guzov, Ilya Petrov",
"author_email": "vguzov@mpi-inf.mpg.de, i.petrov@uni-tuebingen.de",
"download_url": "https://files.pythonhosted.org/packages/48/b5/40126732b6302d1e1885d4f6e6aa9e9e61ddd3f8599b5b5ea90f2d5a7b47/blendify-2.0.0.tar.gz",
"platform": null,
"description": "\n\n## Introduction\nBlendify is a lightweight Python framework that provides a high-level API for creating and rendering scenes with Blender. Developed with a focus on 3D computer vision visualization, Blendify simplifies access to selected Blender functions and objects.\n\nKey features of Blendify:\n\n1. **Simple interface:** Blendify provides a user-friendly interface for performing common visualization tasks without having to dive into the complicated Blender API.\n\n2. **Easy integration:** Blendify seamlessly integrates with development scripts, implementing\ncommonly used routines and functions:\n * native support of point clouds, meshes, and primitives;\n * support of per-vertex colors and textures;\n * advanced shadows with shadow catcher objects;\n * video rendering with smooth camera trajectories;\n * support for common camera models;\n * import and export of .blend files for deeper integration with Blender;\n * per-face definition of materials for meshes;\n * support for common rotation representations and look-at utility to automatically setup orientation.\n3. **Quick start:** Blendify is easy to get started with and does not require a standalone Blender installation. All you need to do is run `pip install blendify`.\n\n4. **Blendify works in Colab:** check out [our Google Colab demo](https://colab.research.google.com/github/ptrvilya/blendify/blob/main/examples/ipynb/blendify_colab_demo.ipynb)!\n\n\n## Installation instructions\n### Install from pip\n```bash\npip install blendify\n```\n### Optional requirements\n```bash\npip install blendify[utils / examples / docs / all]\n```\n\nRunning examples 4 and 5 requires [PyTorch](https://pytorch.org/) with [PyTorch3D](https://github.com/facebookresearch/pytorch3d/blob/main/INSTALL.md).\n\nRunning example 5 requires SMPL model files, please refer to the installation instructions in \n[README](https://github.com/vchoutas/smplx#downloading-the-model).\n\n\n## Quick Start\n```python\n# Script to render cube\nfrom blendify import scene\nfrom blendify.materials import PrincipledBSDFMaterial\nfrom blendify.colors import UniformColors\n# Add light\nscene.lights.add_point(strength=1000, translation=(4, -2, 4))\n# Add camera\nscene.set_perspective_camera((512, 512), fov_x=0.7, rotation=(0.82, 0.42, 0.18, 0.34), translation=(5, -5, 5))\n# Create material\nmaterial = PrincipledBSDFMaterial()\n# Create color\ncolor = UniformColors((0.0, 1.0, 0.0))\n# Add cube mesh\nscene.renderables.add_cube_mesh(1.0, material, color)\n# Render scene\nscene.render(filepath=\"cube.png\")\n```\n\n## Feature walkthrough\nWalkthrough of Blendify features with code and commentaries can be found [here](https://virtualhumans.mpi-inf.mpg.de/blendify/walkthrough.html).\n\n\n## Examples\nCheck examples in our repository [here](https://github.com/ptrvilya/blendify#Examples).\n\n\n## Changelog\nThe most recent version of Blendify is **2.0.0**. The update introduced some breaking changes that are\nsummarized alongside the overview of the new features in the [CHANGELOG](https://github.com/ptrvilya/blendify/blob/main/CHANGELOG.md) file.\n\n## Citation\nIf you use Blendify in your research, please cite:\n```bibtex\n@article{blendify2024,\n title={Blendify -- Python rendering framework for Blender},\n author={Guzov, Vladimir and Petrov, Ilya A and Pons-Moll, Gerard},\n journal={arXiv preprint arXiv:2410.17858},\n year={2024}\n}\n```\n\n\n## Works that use Blendify\n* V. Lazova, E. Insafutdinov, G. Pons-Moll: [360-Degree Textures of People in Clothing from a Single Image](https://virtualhumans.mpi-inf.mpg.de/360tex/)\nin 3DV'19\n* B.L. Bhatnagar, X. Xie, **I. Petrov**, C. Sminchisescu, C. Theobalt, G. Pons-Moll: \n [BEHAVE: Dataset and Method for Tracking Human Object Interactions](https://virtualhumans.mpi-inf.mpg.de/behave/), in CVPR'22\n* X. Zhang, B.L. Bhatnagar, **V. Guzov**, S. Starke, G. Pons-Moll: \n [COUCH: Towards Controllable Human-Chair Interactions](https://virtualhumans.mpi-inf.mpg.de/couch/), in ECCV'22\n* G. Tiwari, D. Antic, J. E. Lenssen, N. Sarafianos, T. Tung, G. Pons-Moll: [Pose-NDF: \nModeling Human Pose Manifolds with Neural Distance Fields](https://virtualhumans.mpi-inf.mpg.de/posendf/), in ECCV'22\n* **I. Petrov**, R. Marin, J. Chibane, G. Pons-Moll: [Object pop-up: Can we infer 3D objects and their poses from human interactions alone?](https://virtualhumans.mpi-inf.mpg.de/object_popup/), in CVPR'23\n\n## Contributors\nBlendify is written and maintained by [Vladimir Guzov](https://github.com/vguzov) and [Ilya Petrov](https://github.com/ptrvilya).\n\n\n## Acknowledgments\nWe thank Verica Lazova for providing her Blender rendering scripts, \n[Istv\u00e1n Sarandi](https://github.com/isarandi) for his suggestions and help in implementing new features, \nand [Riccardo Marin](https://github.com/riccardomarin) for his helpful suggestions and feedback.\nOur code for processing point clouds is mostly based on the amazing [Blender-Photogrammetry-Importer][BPI] addon.\n\n\n## License\nThe code is released under the [GNU General Public License v3][GNU GPL v3].\n\nThe Python logo is trademark of Python Software Foundation.\nThe Blender logo is a registered property of Blender Foundation.\n[Blender-Photogrammetry-Importer][BPI] is distributed under the [MIT License][BPI license]. \nBlender is released under the [GNU General Public License v3][GNU GPL v3]. \n\n[GNU GPL v3]: https://www.gnu.org/licenses/gpl-3.0.html\n[BPI]: https://github.com/SBCV/Blender-Addon-Photogrammetry-Importer\n[BPI license]: https://github.com/SBCV/Blender-Addon-Photogrammetry-Importer/blob/master/README.md\n",
"bugtrack_url": null,
"license": null,
"summary": "Python rendering framework for Blender",
"version": "2.0.0",
"project_urls": {
"Homepage": "https://github.com/ptrvilya/blendify"
},
"split_keywords": [
"rendering",
" pointcloud",
" blender",
" mesh"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "4e2709e26273df514f2ef2ea70010755193c8267b96a6c367df715f0b3060241",
"md5": "080b4c1151081aeb39f2af664bb4be12",
"sha256": "aa48626574477d8a4d75aa5849237e2f546076cad0f8563e3235993cda54957e"
},
"downloads": -1,
"filename": "blendify-2.0.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "080b4c1151081aeb39f2af664bb4be12",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 75043,
"upload_time": "2024-10-24T08:22:14",
"upload_time_iso_8601": "2024-10-24T08:22:14.494510Z",
"url": "https://files.pythonhosted.org/packages/4e/27/09e26273df514f2ef2ea70010755193c8267b96a6c367df715f0b3060241/blendify-2.0.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "48b540126732b6302d1e1885d4f6e6aa9e9e61ddd3f8599b5b5ea90f2d5a7b47",
"md5": "3ff1966da2c43fdae8a55b5dbc9168a3",
"sha256": "ebd0ac357ba4911f7c7bc97e68145581f803ebb2c7f99cf07eb03d0d74bf0136"
},
"downloads": -1,
"filename": "blendify-2.0.0.tar.gz",
"has_sig": false,
"md5_digest": "3ff1966da2c43fdae8a55b5dbc9168a3",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 64004,
"upload_time": "2024-10-24T08:22:15",
"upload_time_iso_8601": "2024-10-24T08:22:15.777389Z",
"url": "https://files.pythonhosted.org/packages/48/b5/40126732b6302d1e1885d4f6e6aa9e9e61ddd3f8599b5b5ea90f2d5a7b47/blendify-2.0.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-10-24 08:22:15",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "ptrvilya",
"github_project": "blendify",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "blendify"
}
JSON
