# cloudrender: an OpenGL framework for pointcloud and mesh rendering
A visualization framework capable of rendering large pointclouds, dynamic SMPL models and more. Used to visualize results in our Human POSEitioning System (HPS) project: http://virtualhumans.mpi-inf.mpg.de/hps/
## Requirements
- GPU with OpenGL 4.0
Optionally, if you want to run included test script:
- EGL support (for headless rendering)
- ffmpeg>=2.1 with libx264 enabled and ffprobe installed (for saving to video)
## Installation
#### Step 1. Get the code
Copy the code without installation
```bash
git clone https://github.com/vguzov/cloudrender
pip install -r requirements.txt
```
or install as a package with
```
pip install cloudrender
```
#### Step 2. Get the SMPL model
- Follow install instructions at https://github.com/gulvarol/smplpytorch
- Make sure to fix the typo for male model while unpacking SMPL .pkl files: `basicmodel_m_lbs_10_207_0_v1.0.0.pkl -> basicModel_m_lbs_10_207_0_v1.0.0.pkl`
## Running test script
### test_scene_video.py
Run `download_test_assets.sh` – it will create `test_assets` folder and download everything you need for sample to work
(3D scan pointcloud, human shape and motion files, camera trajectory file)
Run `test_scene_video.py`
The following script will write a short video inside `test_assets/output.mp4` which should look similar to this:
<p align="center">
<img src="images/test_scene_video_output_example.gif" alt="output example"/>
</p>
## More data
Please check our HPS project page for more 3D scans and motion data: http://virtualhumans.mpi-inf.mpg.de/hps/
## Citation
If you find the code or data useful, please cite:
```
@inproceedings{HPS,
title = {Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors },
author = {Guzov, Vladimir and Mir, Aymen and Sattler, Torsten and Pons-Moll, Gerard},
booktitle = {{IEEE} Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {jun},
organization = {{IEEE}},
year = {2021},
}
```
Raw data
{
"_id": null,
"home_page": "https://github.com/vguzov/cloudrender",
"name": "cloudrender",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": "rendering, pointcloud, opengl, mesh",
"author": "Vladimir Guzov",
"author_email": "vguzov@mpi-inf.mpg.de",
"download_url": "https://files.pythonhosted.org/packages/58/6d/72aefdbb71b7ee109fb82747f8b6899c1d877974b346a8ee91c7de165475/cloudrender-1.3.4.tar.gz",
"platform": null,
"description": "# cloudrender: an OpenGL framework for pointcloud and mesh rendering\nA visualization framework capable of rendering large pointclouds, dynamic SMPL models and more. Used to visualize results in our Human POSEitioning System (HPS) project: http://virtualhumans.mpi-inf.mpg.de/hps/\n\n## Requirements\n- GPU with OpenGL 4.0 \n\nOptionally, if you want to run included test script:\n- EGL support (for headless rendering)\n- ffmpeg>=2.1 with libx264 enabled and ffprobe installed (for saving to video)\n\n## Installation\n#### Step 1. Get the code\nCopy the code without installation\n```bash\ngit clone https://github.com/vguzov/cloudrender\npip install -r requirements.txt\n```\nor install as a package with\n```\npip install cloudrender\n```\n#### Step 2. Get the SMPL model\n- Follow install instructions at https://github.com/gulvarol/smplpytorch\n- Make sure to fix the typo for male model while unpacking SMPL .pkl files: `basicmodel_m_lbs_10_207_0_v1.0.0.pkl -> basicModel_m_lbs_10_207_0_v1.0.0.pkl`\n\n## Running test script\n### test_scene_video.py\nRun `download_test_assets.sh` \u2013 it will create `test_assets` folder and download everything you need for sample to work\n(3D scan pointcloud, human shape and motion files, camera trajectory file)\n\nRun `test_scene_video.py`\n\nThe following script will write a short video inside `test_assets/output.mp4` which should look similar to this:\n<p align=\"center\">\n<img src=\"images/test_scene_video_output_example.gif\" alt=\"output example\"/>\n</p>\n\n## More data\nPlease check our HPS project page for more 3D scans and motion data: http://virtualhumans.mpi-inf.mpg.de/hps/\n\n## Citation\n\nIf you find the code or data useful, please cite: \n\n```\n@inproceedings{HPS,\n title = {Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors },\n author = {Guzov, Vladimir and Mir, Aymen and Sattler, Torsten and Pons-Moll, Gerard},\n booktitle = {{IEEE} Conference on Computer Vision and Pattern Recognition (CVPR)},\n month = {jun},\n organization = {{IEEE}},\n year = {2021},\n}\n```\n",
"bugtrack_url": null,
"license": null,
"summary": "An OpenGL framework for pointcloud and mesh rendering",
"version": "1.3.4",
"project_urls": {
"Homepage": "https://github.com/vguzov/cloudrender"
},
"split_keywords": [
"rendering",
" pointcloud",
" opengl",
" mesh"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "542fe59a9b62629b5c97da047f270185e8200695198b01fdffba7f544d14d41c",
"md5": "21b0cc4ecbd0542ea55d36eb4961d4f3",
"sha256": "eb11fdbaacec3ae592e3c0e26c4ed1bd784bdb2e0d73d714672eebbb05efe542"
},
"downloads": -1,
"filename": "cloudrender-1.3.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "21b0cc4ecbd0542ea55d36eb4961d4f3",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 73408,
"upload_time": "2024-09-12T16:03:25",
"upload_time_iso_8601": "2024-09-12T16:03:25.269860Z",
"url": "https://files.pythonhosted.org/packages/54/2f/e59a9b62629b5c97da047f270185e8200695198b01fdffba7f544d14d41c/cloudrender-1.3.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "586d72aefdbb71b7ee109fb82747f8b6899c1d877974b346a8ee91c7de165475",
"md5": "46db189c54d11912c2b055fc84175393",
"sha256": "e3731c9ebe537229da041c89171cd9f17ce095879e1ac605e6e20713d96e1716"
},
"downloads": -1,
"filename": "cloudrender-1.3.4.tar.gz",
"has_sig": false,
"md5_digest": "46db189c54d11912c2b055fc84175393",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 40212,
"upload_time": "2024-09-12T16:03:26",
"upload_time_iso_8601": "2024-09-12T16:03:26.828977Z",
"url": "https://files.pythonhosted.org/packages/58/6d/72aefdbb71b7ee109fb82747f8b6899c1d877974b346a8ee91c7de165475/cloudrender-1.3.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-09-12 16:03:26",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "vguzov",
"github_project": "cloudrender",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [],
"lcname": "cloudrender"
}
JSON
