stevenygd/NFGP

Pytorch implementation of NeurIPS 2021 paper: Geometry Processing with Neural Fields.

32
/ 100
Emerging

This project helps 3D designers and engineers manipulate complex 3D shapes without the typical issues of mesh-based modeling. It takes a 3D model (like an OBJ file) as input, converts it into a neural field representation, and allows for operations such as smoothing, sharpening, or deforming the shape. The output is a modified 3D shape, offering a more flexible approach to geometry processing.

204 stars. No commits in the last 6 months.

Use this if you need to perform advanced deformations, smoothing, or sharpening on 3D models and want to avoid the complexities and limitations associated with traditional mesh editing, especially for shapes with intricate or changing topologies.

Not ideal if you primarily work with simple, rigid 3D models where basic mesh-editing tools are sufficient and you don't require high-order derivative optimizations or topological flexibility.

3D modeling computer graphics shape deformation geometric design computational geometry
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

204

Forks

19

Language

Jupyter Notebook

License

Last pushed

Oct 25, 2023

Commits (30d)

0

Get this data via API

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

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