DLR-RM/NeMO

Official Repository for "Finding NeMO: A Geometry-Aware Representation of Template Views for Few-Shot Perception"

29
/ 100
Experimental

This project helps robotics engineers and computer vision scientists quickly teach a system to recognize new objects from just a few images. You provide a small set of pictures of an object, and it outputs a 'Neural Memory Object' that allows the system to identify, segment, and determine the exact 3D position and orientation of that object in new images or videos.

Use this if you need to rapidly train a computer vision system to recognize specific objects and their 3D poses without needing a large dataset of example images.

Not ideal if you are looking for a general-purpose object detection system that doesn't require specific object identification or 3D pose estimation from limited examples.

robotics computer-vision object-recognition 3d-pose-estimation few-shot-learning
No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 13 / 25
Community 0 / 25

How are scores calculated?

Stars

15

Forks

Language

Python

License

MIT

Last pushed

Feb 17, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/DLR-RM/NeMO"

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