JianfeiJ/RRT-MVS

[AAAI 2025] RRT-MVS: Recurrent Regularization Transformer for Multi-View Stereo

27
/ 100
Experimental

This project helps create highly accurate 3D models of objects and environments from multiple 2D images. It takes a collection of photographs taken from different angles of a scene and produces detailed 3D point clouds, which are essentially dense collections of points representing the surface of the object. This is ideal for professionals in fields like 3D scanning, cultural heritage preservation, or industrial inspection who need precise spatial reconstructions.

Use this if you need to generate highly accurate and detailed 3D point clouds from multiple input images, especially for complex scenes with fine details and challenging depth variations.

Not ideal if you only need rough 3D models or if you are working with single images, as this method requires multiple views for its core functionality.

3D-reconstruction photogrammetry spatial-modeling digital-preservation industrial-metrology
No Package No Dependents
Maintenance 6 / 25
Adoption 6 / 25
Maturity 15 / 25
Community 0 / 25

How are scores calculated?

Stars

15

Forks

Language

Python

License

MIT

Last pushed

Nov 04, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/JianfeiJ/RRT-MVS"

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