JohnRomanelis/SPVD
SPVD: Efficient and Scalable Point Cloud Generation with Sparse Point-Voxel Diffusion Models
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.
Stars
60
Forks
2
Language
Jupyter Notebook
License
MIT
Category
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.
Higher-rated alternatives
PRIS-CV/DemoFusion
Let us democratise high-resolution generation! (CVPR 2024)
mit-han-lab/distrifuser
[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
Tencent-Hunyuan/HunyuanPortrait
[CVPR-2025] The official code of HunyuanPortrait: Implicit Condition Control for Enhanced...
giuvecchio/matfuse
MatFuse: Controllable Material Generation with Diffusion Models (CVPR2024)
Shilin-LU/TF-ICON
[ICCV 2023] "TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition" (Official...