3D computer vision library in Julia
Author FluxML
54 Stars
Updated Last
2 Years Ago
Started In
April 2020


Flux3D.jl 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.The primary motivation for this library is to provide:

  • Batched Data structure for 3D data like PointCloud, TriMesh and VoxelGrid for storing and computation.
  • Transforms and general utilities for processing 3D structures.
  • Metrics for defining loss objectives and predefined 3D models.
  • Easy access to loading and pre-processing standard 3D datasets.
  • Visualization utilities for PointCloud, TriMesh and VoxelGrid.
  • Inter-Conversion between different 3D structures.

Any suggestions, issues and pull requests are most welcome.


This package is stable enough for use in 3D Machine Learning Research. It has been registered. To install the latest release, type the following in the Julia 1.3+ prompt.

julia> ]
(v1.3) pkg> add Flux3D

To install the master branch type the following

julia> ]
(v1.3) pkg> add Flux3D#master


Usage Examples

julia> using Flux3D

julia> m = load_trimesh("teapot.obj") |> gpu
TriMesh{Float32, UInt32, CUDA.CuArray} Structure:
    Batch size: 1
    Max verts: 1202
    Max faces: 2256
    offset: -1
    Storage type: CUDA.CuArray

julia> laplacian_loss(m)

julia> compute_verts_normals_packed(m)
3×1202 CUDA.CuArray{Float32,2,Nothing}:
  0.00974202   0.00940375   0.01713220.841262   0.777704   0.812894
 -0.999953    -0.999953    -0.999848       -0.508064  -0.607522  -0.557358
  6.14616f-6   0.00249814  -0.00317568     -0.184795  -0.161533  -0.168985

julia> new_m = Flux3D.normalize(m)
TriMesh{Float32, UInt32, CUDA.CuArray} Structure:
    Batch size: 1
    Max verts: 1202
    Max faces: 2256
    offset: -1
    Storage type: CUDA.CuArray

julia> save_trimesh("normalized_teapot.obj", new_m)


If you use this software as a part of your research or teaching, please cite this GitHub repository. For convenience, we have also provided the BibTeX entry in the form of CITATION.bib file.

    author = {Nirmal Suthar, Avik Pal, Dhairya Gandhi},
    title = {Flux3D: A Framework for 3D Deep Learning in Julia},
    year = {2020},
    publisher = {GitHub},
    journal = {GitHub repository},
    howpublished = {\url{https://github.com/FluxML/Flux3D.jl}},


PointCloud Transforms (Flux3D.jl and Kaolin)

Benchmark plot for PointCloud transforms

TriMesh Transforms (Flux3D.jl and Kaolin)

Benchmark plot for TriMesh transforms

Metrics (Flux3D.jl and Kaolin)

Benchmark plot for Metrics

Current Roadmap

  • Add Batched Structure for PointCloud and TriMesh.
  • Add Transforms/Metrics for PointCloud and TriMesh.
  • GPU Support using CUDA.jl
  • Add Dataset support for ModelNet10/40.
  • Add Batched 3D structure and Transform for Voxels.
  • Interconversion between different 3D structures like PointCloud, Voxel and TriMesh.
  • Add more metrics for TriMesh (like normal_consistency and cloud_mesh_distance)

Used By Packages

No packages found.