ErlerPhilipp/points2surf
Learning Implicit Surfaces from Point Clouds (ECCV 2020)
This project helps engineers, designers, or researchers reconstruct 3D models from raw 3D scan data. It takes in point clouds, which are collections of data points defining the exterior of an object, and outputs a clean, watertight 3D mesh model. This tool is ideal for anyone working with real-world 3D scan data who needs to convert it into usable 3D geometries for modeling or analysis.
508 stars. No commits in the last 6 months.
Use this if you need to accurately convert messy 3D point cloud scans into high-quality, manifold 3D mesh models.
Not ideal if you primarily work with existing 3D mesh data or need to generate point clouds from CAD models rather than reconstructing from raw scans.
Stars
508
Forks
51
Language
Python
License
MIT
Category
Last pushed
Aug 06, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ErlerPhilipp/points2surf"
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