pvnieo/DPFM

Pytorch code for "DPFM: Deep Partial Functional Maps" - 3DV 2021 (Oral)

34
/ 100
Emerging

This tool helps researchers and engineers working with 3D models to automatically find correspondences between shapes, even when parts of one shape are missing or occluded. You provide a collection of 3D meshes and some examples of how points on these shapes map to each other, and it outputs a model that can predict these correspondences for new, incomplete 3D shapes. It's designed for professionals in computer graphics, vision, and related fields who analyze and compare 3D geometries.

No commits in the last 6 months.

Use this if you need to establish accurate point-to-point mappings between non-rigid 3D shapes where one or both shapes might have missing or partially occluded areas.

Not ideal if your task involves only complete 3D shapes or if you require mappings between entirely different object categories rather than variations of similar shapes.

3D-model-analysis shape-matching computer-graphics 3D-vision geometric-modeling
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

42

Forks

4

Language

Python

License

GPL-3.0

Last pushed

Aug 12, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/pvnieo/DPFM"

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