| Name | torchhull JSON |
| Version |
0.2.0
JSON |
| download |
| home_page | None |
| Summary | A fast Visual Hull implementation |
| upload_time | 2025-07-10 13:28:07 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.9 |
| license | None |
| keywords |
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
<h1 align="center">torchhull: A fast Visual Hull implementation</h1>
<!-- start readme -->
<p align="center">
<a href="https://pypi.python.org/pypi/torchhull">
<img alt="PyPI - Version" src="https://img.shields.io/pypi/v/torchhull">
</a>
<a href="https://pypi.python.org/pypi/torchhull">
<img alt="PyPI - Python Version" src="https://img.shields.io/pypi/pyversions/torchhull">
</a>
<a href="https://github.com/vc-bonn/torchhull/blob/main/LICENSE">
<img alt="GitHub License" src="https://img.shields.io/badge/License-MIT-green.svg"/>
</a>
<a href="https://github.com/vc-bonn/torchhull/blob/main/LICENSE">
<img alt="GitHub License" src="https://img.shields.io/badge/License-BSD--3--Clause-green.svg"/>
</a>
<a href="https://github.com/vc-bonn/torchhull/actions/workflows/build.yml">
<img alt="Build" src="https://github.com/vc-bonn/torchhull/actions/workflows/build.yml/badge.svg">
</a>
<a href="https://github.com/vc-bonn/torchhull/actions/workflows/lint.yml">
<img alt="Lint" src="https://github.com/vc-bonn/torchhull/actions/workflows/lint.yml/badge.svg">
</a>
<a href="https://vc-bonn.github.io/torchhull">
<img alt="Documentation" src="https://img.shields.io/badge/docs-Latest-green.svg"/>
</a>
</p>
torchhull is an extremely fast Torch C++/CUDA implementation for computing visual hulls from mask images and comes with Python bindings through [charonload](https://github.com/vc-bonn/charonload):
- ⚡ Up to real-time capable speed depending on chosen resolution
- 🗜️ Memory-efficient computation by constructing sparse voxel octrees
- 🌊 Watertight mesh generation via Marching Cubes
- 🎈 Smooth surfaces with sparse Gaussian blur preprocessing tailored for mask images
- 🛠️ Support for partially visible objects, i.e. clipped mask images, and fully observed objects
In particular, torchhull is a GPU implementation of the following paper:
```bib
@article{scharr2017fast,
title={{Fast High Resolution Volume Carving for 3D Plant Shoot Reconstruction}},
author={Scharr, Hanno and Briese, Christoph and Embgenbroich, Patrick and Fischbach, Andreas and Fiorani, Fabio and M{\"u}ller-Linow, Mark},
journal={Frontiers in Plant Science},
volume={8},
pages={303692},
year={2017},
publisher={Frontiers}
}
```
## Installation
torchhull requires the following prerequites (for JIT compilation):
- Python >= 3.9
- CUDA >= 12.1
- C++17 compiler
The package itself can be installed from PyPI:
```sh
pip install torchhull
```
## Quick Start
torchhull gets as input mask images with camera information:
- `masks`: Single-channel images `M` with binary values {0, 1}.
- `transforms`: Fused extrinsic and intrinsic matrix `K * T`, i.e. transformation from world coordinates to OpenGL clip space (right before perspective division).
The visual hull is then evaluated inside a cube with bottom-front-left corner `cube_corner_bfl` and extent `cube_length` at extracted at octree level `level`. The remaining flags control how the output mesh `(verts, faces)` should look like.
```python
import torchhull
# Optional
masks = torchhull.gaussian_blur(masks, # [B, H, W, 1]
kernel_size,
sigma,
sparse=True,
)
verts, faces = torchhull.visual_hull(masks, # [B, H, W, 1]
transforms, # [B, 4, 4]
level,
cube_corner_bfl,
cube_length,
masks_partial=False,
unique_verts=True,
)
```
## License
This software is provided under MIT license, with parts under BSD 3-Clause license. See [`LICENSE`](https://github.com/vc-bonn/torchhull/blob/main/LICENSE) for more information.
## Contact
Patrick Stotko - <a href="mailto:stotko@cs.uni-bonn.de">stotko@cs.uni-bonn.de</a><br/>
<!-- end readme -->
Raw data
{
"_id": null,
"home_page": null,
"name": "torchhull",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.9",
"maintainer_email": null,
"keywords": null,
"author": null,
"author_email": "Patrick Stotko <stotko@cs.uni-bonn.de>",
"download_url": "https://files.pythonhosted.org/packages/7b/91/b56545de3cbd38f915a792055deea78f6908138a9ad2b7549816f2f17987/torchhull-0.2.0.tar.gz",
"platform": null,
"description": "<h1 align=\"center\">torchhull: A fast Visual Hull implementation</h1>\n\n<!-- start readme -->\n\n<p align=\"center\">\n<a href=\"https://pypi.python.org/pypi/torchhull\">\n <img alt=\"PyPI - Version\" src=\"https://img.shields.io/pypi/v/torchhull\">\n</a>\n<a href=\"https://pypi.python.org/pypi/torchhull\">\n <img alt=\"PyPI - Python Version\" src=\"https://img.shields.io/pypi/pyversions/torchhull\">\n</a>\n<a href=\"https://github.com/vc-bonn/torchhull/blob/main/LICENSE\">\n <img alt=\"GitHub License\" src=\"https://img.shields.io/badge/License-MIT-green.svg\"/>\n</a>\n<a href=\"https://github.com/vc-bonn/torchhull/blob/main/LICENSE\">\n <img alt=\"GitHub License\" src=\"https://img.shields.io/badge/License-BSD--3--Clause-green.svg\"/>\n</a>\n<a href=\"https://github.com/vc-bonn/torchhull/actions/workflows/build.yml\">\n <img alt=\"Build\" src=\"https://github.com/vc-bonn/torchhull/actions/workflows/build.yml/badge.svg\">\n</a>\n<a href=\"https://github.com/vc-bonn/torchhull/actions/workflows/lint.yml\">\n <img alt=\"Lint\" src=\"https://github.com/vc-bonn/torchhull/actions/workflows/lint.yml/badge.svg\">\n</a>\n<a href=\"https://vc-bonn.github.io/torchhull\">\n <img alt=\"Documentation\" src=\"https://img.shields.io/badge/docs-Latest-green.svg\"/>\n</a>\n</p>\n\n\ntorchhull is an extremely fast Torch C++/CUDA implementation for computing visual hulls from mask images and comes with Python bindings through [charonload](https://github.com/vc-bonn/charonload):\n\n- \u26a1 Up to real-time capable speed depending on chosen resolution\n- \ud83d\udddc\ufe0f Memory-efficient computation by constructing sparse voxel octrees\n- \ud83c\udf0a Watertight mesh generation via Marching Cubes\n- \ud83c\udf88 Smooth surfaces with sparse Gaussian blur preprocessing tailored for mask images\n- \ud83d\udee0\ufe0f Support for partially visible objects, i.e. clipped mask images, and fully observed objects\n\n\nIn particular, torchhull is a GPU implementation of the following paper:\n\n```bib\n@article{scharr2017fast,\n title={{Fast High Resolution Volume Carving for 3D Plant Shoot Reconstruction}},\n author={Scharr, Hanno and Briese, Christoph and Embgenbroich, Patrick and Fischbach, Andreas and Fiorani, Fabio and M{\\\"u}ller-Linow, Mark},\n journal={Frontiers in Plant Science},\n volume={8},\n pages={303692},\n year={2017},\n publisher={Frontiers}\n}\n```\n\n\n## Installation\n\ntorchhull requires the following prerequites (for JIT compilation):\n\n- Python >= 3.9\n- CUDA >= 12.1\n- C++17 compiler\n\nThe package itself can be installed from PyPI:\n\n```sh\npip install torchhull\n```\n\n\n## Quick Start\n\ntorchhull gets as input mask images with camera information:\n\n- `masks`: Single-channel images `M` with binary values {0, 1}.\n- `transforms`: Fused extrinsic and intrinsic matrix `K * T`, i.e. transformation from world coordinates to OpenGL clip space (right before perspective division).\n\nThe visual hull is then evaluated inside a cube with bottom-front-left corner `cube_corner_bfl` and extent `cube_length` at extracted at octree level `level`. The remaining flags control how the output mesh `(verts, faces)` should look like.\n\n```python\nimport torchhull\n\n# Optional\nmasks = torchhull.gaussian_blur(masks, # [B, H, W, 1]\n kernel_size,\n sigma,\n sparse=True,\n )\n\nverts, faces = torchhull.visual_hull(masks, # [B, H, W, 1]\n transforms, # [B, 4, 4]\n level,\n cube_corner_bfl,\n cube_length,\n masks_partial=False,\n unique_verts=True,\n )\n```\n\n\n## License\n\nThis software is provided under MIT license, with parts under BSD 3-Clause license. See [`LICENSE`](https://github.com/vc-bonn/torchhull/blob/main/LICENSE) for more information.\n\n\n## Contact\n\nPatrick Stotko - <a href=\"mailto:stotko@cs.uni-bonn.de\">stotko@cs.uni-bonn.de</a><br/>\n\n<!-- end readme -->\n",
"bugtrack_url": null,
"license": null,
"summary": "A fast Visual Hull implementation",
"version": "0.2.0",
"project_urls": {
"Changelog": "https://github.com/vc-bonn/torchhull/blob/main/CHANGELOG.md",
"Documentation": "https://vc-bonn.github.io/torchhull/",
"Homepage": "https://github.com/vc-bonn/torchhull",
"Repository": "https://github.com/vc-bonn/torchhull"
},
"split_keywords": [],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "35e586ec1eba022056bbc535e716320ebd010ebaaf4dd96ba8cf2e56931e56bf",
"md5": "e9e1d1db01272d8e03e5701da3710a5a",
"sha256": "be111468b41a99db0847956bc3b8f891a41d3b09e09beb82c5a27443881c1427"
},
"downloads": -1,
"filename": "torchhull-0.2.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "e9e1d1db01272d8e03e5701da3710a5a",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.9",
"size": 40234,
"upload_time": "2025-07-10T13:28:06",
"upload_time_iso_8601": "2025-07-10T13:28:06.107321Z",
"url": "https://files.pythonhosted.org/packages/35/e5/86ec1eba022056bbc535e716320ebd010ebaaf4dd96ba8cf2e56931e56bf/torchhull-0.2.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "7b91b56545de3cbd38f915a792055deea78f6908138a9ad2b7549816f2f17987",
"md5": "ce6abb7e00b4118a9b87a6fc8a4b0f86",
"sha256": "82bc55149a8ded281676da38b6059943a96679c402a671e511e3acf2e15a0ccf"
},
"downloads": -1,
"filename": "torchhull-0.2.0.tar.gz",
"has_sig": false,
"md5_digest": "ce6abb7e00b4118a9b87a6fc8a4b0f86",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.9",
"size": 39444,
"upload_time": "2025-07-10T13:28:07",
"upload_time_iso_8601": "2025-07-10T13:28:07.511691Z",
"url": "https://files.pythonhosted.org/packages/7b/91/b56545de3cbd38f915a792055deea78f6908138a9ad2b7549816f2f17987/torchhull-0.2.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-10 13:28:07",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "vc-bonn",
"github_project": "torchhull",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "torchhull"
}
