cvg/diffmvs

[T-PAMI 2025] DiffMVS & CasDiffMVS

40
/ 100
Emerging

This project helps generate highly detailed and accurate 3D models from a collection of photographs taken from different angles. It takes a set of images of an object or scene, along with their camera positions, and outputs a dense 3D point cloud, which is a digital representation of the scene's geometry. This tool is ideal for professionals in fields like surveying, cultural heritage preservation, or industrial inspection who need precise 3D reconstructions.

157 stars.

Use this if you need to create accurate and lightweight 3D models from multiple photographs, especially when balancing reconstruction quality with computational efficiency is crucial.

Not ideal if you only have a single image or already have a sparse point cloud and don't require further dense reconstruction.

3D-reconstruction photogrammetry cultural-heritage industrial-inspection spatial-mapping
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

157

Forks

7

Language

Python

License

Apache-2.0

Last pushed

Dec 24, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/cvg/diffmvs"

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