andreasMazur/geoconv

A Python library for end-to-end learning on surfaces. It implements pre-processing functions that include geodesic algorithms, neural network layers that operate on surfaces, visualization tools and benchmarking functionalities.

50
/ 100
Established

This tool helps researchers and engineers build deep learning models that can analyze the shapes and characteristics of 3D objects, specifically those represented as mesh files. It takes a 3D mesh (like a .ply file) and a signal defined on its surface, then processes them to produce a structured output ready for neural network analysis or classification. It is used by anyone working with 3D object data who needs to apply deep learning for tasks like shape recognition, object classification, or analyzing physical properties on curved surfaces.

Available on PyPI.

Use this if you need to apply deep learning to 3D object surfaces and want to use intrinsic convolutions that respect the object's geometry, rather than treating it as flat data.

Not ideal if your data is primarily flat (Euclidean) or if you are working with unstructured point clouds without mesh connectivity.

3D-object-analysis geometric-deep-learning shape-recognition computer-graphics computational-geometry
Maintenance 10 / 25
Adoption 7 / 25
Maturity 25 / 25
Community 8 / 25

How are scores calculated?

Stars

37

Forks

3

Language

Python

License

GPL-3.0

Last pushed

Mar 13, 2026

Commits (30d)

0

Dependencies

10

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/andreasMazur/geoconv"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.