mauriceqch/2021_pc_perceptual_loss
A deep perceptual metric for 3D point clouds
This project helps researchers and engineers evaluate the visual quality of 3D point clouds. It takes a distorted 3D point cloud and a reference point cloud, then outputs a score that reflects how a human would perceive the quality or distortion. It's designed for professionals working with 3D data compression, streaming, or rendering who need to quantify visual fidelity.
Use this if you need an automated, objective way to measure the perceived visual quality of 3D point clouds, especially for research or development in graphics and computer vision.
Not ideal if you are looking for tools to generate or manipulate 3D models, or if your primary need is for geometric accuracy metrics rather than perceptual ones.
Stars
14
Forks
2
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Feb 06, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mauriceqch/2021_pc_perceptual_loss"
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