Dear Julia Community,
I am really excited to share Flux3D.jl with all. It is a 3D vision library, written completely in Julia. This package utilizes Flux.jl and Zygote.jl as its building blocks for training 3D vision models and for supporting differentiation. This package also have support of CUDA GPU acceleration with CUDA.jl. Some of the main features include:-
- Batched Data structure for 3D data like PointCloud, TriMesh and VoxelGrid for storing and computation.
- Transforms and general utilities for processing 3D structures like rotation, scale, normalize and etc.
- Metrics for defining loss objectives and predefined 3D models like chamfer_distance, laplacian_loss and edge_loss.
- Easy access to loading and pre-processing ModelNet10/40 dataset in multiple 3D structures.
- Visualization utilities for PointCloud, TriMesh and VoxelGrid.
- Inter-Conversion between different 3D structures.
We believe it is stable enough for use in 3D vision tasks and It has been registered. Following are some relevant links, which provide greater details of the functionality and need of this library.
- Flux3D.jl : github.com/FluxML/Flux3D.jl
- Docs : fluxml.ai/Flux3D.jl/stable/
- Blog Post : nextjournal.com/nirmal-suthar/flux3d-jl