huangjh-pub/synorim
[T-PAMI'22] [Jittor & Pytorch] Multiway Non-rigid Point Cloud Registration via Learned Functional Map Synchronization
This tool helps researchers and engineers align multiple 3D scans (point clouds) of objects that can deform or change shape, like the same person's face captured from different angles. It takes a collection of non-rigid 3D point clouds as input and outputs a set of accurately aligned 3D models. Anyone working with 3D scanning, modeling, or reconstruction in fields like computer vision or graphics would find this useful.
133 stars. No commits in the last 6 months.
Use this if you need to precisely match and align several deformable 3D scans, even when objects have undergone non-rigid transformations.
Not ideal if you are working with rigid objects that don't change shape, as simpler alignment methods might be more efficient.
Stars
133
Forks
12
Language
Python
License
—
Category
Last pushed
Oct 27, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/huangjh-pub/synorim"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
daavoo/pyntcloud
pyntcloud is a Python library for working with 3D point clouds.
yangyanli/PointCNN
PointCNN: Convolution On X-Transformed Points (NeurIPS 2018)
torch-points3d/torch-points3d
Pytorch framework for doing deep learning on point clouds.
yogeshhk/MidcurveNN
Computation of Midcurve of Thin Polygons using Neural Networks
charlesq34/pointnet2
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space