nianticlabs/acezero

[ECCV 2024 - Oral] ACE0 is a learning-based structure-from-motion approach that estimates camera parameters of sets of images by learning a multi-view consistent, implicit scene representation.

47
/ 100
Emerging

This project helps anyone working with collections of images captured from different viewpoints, like drone footage or photo sets of a location. It takes those images and automatically determines the precise camera position and orientation (poses) for each one, along with generating a 3D understanding of the scene. This output is crucial for tasks like creating 3D models or virtual tours.

805 stars.

Use this if you need to automatically and accurately calculate camera poses and reconstruct a 3D scene from a diverse set of images without manual intervention.

Not ideal if you only have a single image or your images lack sufficient overlap to reconstruct a 3D environment.

3D-reconstruction photogrammetry robotics-localization augmented-reality computer-vision
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

805

Forks

56

Language

Python

License

Last pushed

Nov 10, 2025

Commits (30d)

0

Get this data via API

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

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