Efficient operations for fusing semantically annotated RGB-D measurements in a 3D voxel grid in pytorch.
Project description
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 following the structure of DirectVoxGO.
Setup
pip install grid-fusion-pytorch
Requirements
PyTorch must be installed with CUDA support. Also, Ninja is required to load C++ extensions. Install it with pip.
pip install ninja
Usage
Check out the colab demo.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
grid_fusion_pytorch-0.1.1.tar.gz
(29.8 kB
view hashes)
Built Distribution
Close
Hashes for grid_fusion_pytorch-0.1.1.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 4e8cbdb830eae52f71ecc120d70f14e4d923f576b38a1b038c8241f9d9fb781d |
|
MD5 | 0c2ff58dbebf29de6879728aaf0d5bba |
|
BLAKE2b-256 | 91cd1668bdbc671ccebef0822738021cf2d767e2e7b26a8555a29c431f8a68fa |
Close
Hashes for grid_fusion_pytorch-0.1.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | c8c4caa589d3162ad1667cc09aafa94cd5d0692f0d5f65810930539efeddd1b2 |
|
MD5 | a52a4966d666b9f556b859c7dce4963a |
|
BLAKE2b-256 | fce2882c8d9a26133f61ff88101a86a3a2ba2994054b693dfb3cc6d9b23e5731 |