Gorilla-Lab-SCUT/AnalyticMesh
An Efficient Implementation of Analytic Mesh Algorithm for 3D Iso-surface Extraction from Neural Networks
This tool helps 3D modelers and researchers accurately extract complex 3D shapes (iso-surfaces) from deep implicit surface networks. It takes a neural network model, typically an ONNX file, as input and produces a watertight 3D mesh (PLY file) that precisely represents the network's defined surface. This is ideal for those needing highly accurate, error-free 3D models derived from neural network representations, especially in fields like computer graphics, CAD, or medical imaging.
No commits in the last 6 months.
Use this if you need to extract precise, topologically and geometrically correct 3D meshes from deep implicit surface networks without the sampling errors common in other meshing methods.
Not ideal if your primary goal is rapid, approximate 3D model generation and you are not working with neural network-based surface definitions.
Stars
76
Forks
5
Language
C++
License
MIT
Category
Last pushed
May 13, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Gorilla-Lab-SCUT/AnalyticMesh"
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