JohnRomanelis/SPVD

SPVD: Efficient and Scalable Point Cloud Generation with Sparse Point-Voxel Diffusion Models

35
/ 100
Emerging

This project helps researchers and engineers working with 3D models to generate, complete, or enhance 'point clouds' – 3D data represented as many individual points. You can input incomplete 3D scans or general 3D model categories and receive high-quality, dense 3D point cloud models. It's designed for professionals in fields like 3D computer vision, robotics, or design who need to work with or synthesize realistic 3D object representations.

Use this if you need to create realistic 3D point cloud data from scratch, fill in missing parts of a 3D scan, or increase the detail of existing low-resolution 3D point clouds.

Not ideal if you are looking for a simple drag-and-drop tool for general 3D modeling or if your primary interest is in traditional mesh-based 3D graphics.

3D Computer Vision Point Cloud Processing 3D Model Generation Robotics Simulation Digital Prototyping
No Package No Dependents
Maintenance 6 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

60

Forks

2

Language

Jupyter Notebook

License

MIT

Last pushed

Dec 08, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/JohnRomanelis/SPVD"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.