ranahanocka/MeshCNN
Convolutional Neural Network for 3D meshes in PyTorch
This project helps classify and segment 3D objects represented as triangular meshes. You input a 3D mesh, and it outputs either a label for the entire object (like 'alien' or 'human') or highlights different parts of the object with distinct labels (like 'arm' or 'leg'). This is useful for researchers and professionals working with 3D models in fields like computer graphics, robotics, or design.
1,718 stars. No commits in the last 6 months.
Use this if you need to automatically identify entire 3D shapes or categorize specific regions within a 3D mesh.
Not ideal if your 3D data is in a format other than triangular meshes, such as point clouds or volumetric data, or if you need to generate new 3D models.
Stars
1,718
Forks
343
Language
Python
License
MIT
Category
Last pushed
Feb 07, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ranahanocka/MeshCNN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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