Metadata-Version: 2.1
Name: grid_fusion_pytorch
Version: 0.1.1
Summary: Efficient operations for fusing semantically annotated RGB-D measurements in a 3D voxel grid in pytorch.
Author-email: Jan Nogga <nogga@ais.uni-bonn.de>
License: GNU General Public License v3 (GPLv3)
Project-URL: Homepage, https://github.com/JanNogga/grid_fusion_pytorch
Project-URL: Bug Tracker, https://github.com/JanNogga/grid_fusion_pytorch/issues
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
Classifier: Operating System :: OS Independent
Requires-Python: >=3.7
Description-Content-Type: text/markdown
License-File: LICENSE

# grid_fusion_pytorch
Efficient operations for fusing depth maps or point clouds with or without semantic annotation in a 3D voxel grid in pytorch. Corresponding backward passes are WIP.
Uses [TORCH.UTILS.CPP_EXTENSION](https://pytorch.org/docs/stable/cpp_extension.html#torch-utils-cpp-extension) following the structure of [DirectVoxGO](https://github.com/sunset1995/DirectVoxGO).

## Setup
```console
pip install grid-fusion-pytorch
```

## Requirements
[PyTorch](https://pytorch.org/get-started/locally/) must be installed with CUDA support. Also, [Ninja](https://ninja-build.org/) is required to load C++ extensions. Install it with pip.

```console
pip install ninja
```

## Usage
Check out the [colab demo](https://colab.research.google.com/github/JanNogga/grid_fusion_pytorch/blob/main/example_colab.ipynb).
