3D augmentation and transforms of 2D/3D sparse data, such as 3D triangle meshes or point clouds in Euclidean space. Extension of the Fast.ai library to train Sub-manifold Sparse Convolution Networks
This is an extension of the fast.ai library to train Submanifold Sparse Convolution Networks that apply to 2D/3D sparse data, such as 3D geometric meshes or point clouds in euclidian space
Currently, this library has SparseConvNet under the hood which is the best in 3D (ScanNet benchmark, ShapeNet workshop) so far.
fastai_sparse is compatible with: Python 3.6, PyTorch 1.0+
Some key dependences:
See details in INSTALL.md