FangjinhuaWang/IterMVS

Official code of IterMVS (CVPR 2022)

43
/ 100
Emerging

IterMVS helps generate highly accurate 3D point clouds from multiple 2D images of a scene, a process known as Multi-View Stereo (MVS). You input a set of images of an object or scene along with their camera parameters, and it outputs a detailed 3D point cloud in PLY format. This is ideal for researchers in computer vision or anyone needing to reconstruct high-fidelity 3D models from visual data.

170 stars. No commits in the last 6 months.

Use this if you need to create precise 3D reconstructions of objects or scenes from multiple photographs efficiently, especially for research in 3D vision.

Not ideal if you require a user-friendly application with a graphical interface for 3D reconstruction, as this project is a research-oriented codebase.

3D reconstruction Computer Vision Research Photogrammetry 3D scanning Depth estimation
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

170

Forks

19

Language

Python

License

MIT

Last pushed

Sep 19, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/FangjinhuaWang/IterMVS"

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