alekseizhuravlev/denoising-functional-maps

[CVPR'2025] Denoising Functional Maps: Diffusion Models for Shape Correspondence

24
/ 100
Experimental

This project helps researchers and practitioners in computer graphics and 3D vision accurately align different 3D shapes, even when they have noise or variations. It takes two 3D mesh models as input and produces a detailed, point-to-point correspondence showing how one shape maps onto the other. This is ideal for those working with 3D model analysis, animation, or medical imaging.

No commits in the last 6 months.

Use this if you need to find precise correspondences between complex 3D shapes, especially when dealing with noisy or slightly different models.

Not ideal if you only need rough shape alignment or are working with simple 2D images instead of 3D meshes.

3D-model-alignment shape-analysis computer-graphics 3D-vision mesh-processing
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

16

Forks

Language

Python

License

MIT

Last pushed

Jul 31, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/alekseizhuravlev/denoising-functional-maps"

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