superbijk/pytorch_pcd_metrics
PyTorch CUDA accelerated evaluation metrics for point cloud generation; All right are given to original authors
This is a specialized developer tool for evaluating point cloud generation models. It takes two sets of point clouds – one generated by your model and one ground truth – and calculates various metrics to quantify how similar they are. This helps researchers and developers working on 3D computer vision and graphics to assess the quality and performance of their point cloud generation algorithms.
Use this if you are a developer or researcher building and evaluating deep learning models that generate 3D point clouds and need to quantify their performance using standard metrics.
Not ideal if you are an end-user simply viewing or manipulating 3D models and not actively developing the underlying generation algorithms.
Stars
8
Forks
1
Language
Cuda
License
MIT
Category
Last pushed
Nov 20, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/superbijk/pytorch_pcd_metrics"
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