gist-ailab/uoais

Codes of paper "Unseen Object Amodal Instance Segmentation via Hierarchical Occlusion Modeling", ICRA 2022

47
/ 100
Emerging

This project helps industrial automation and robotics engineers accurately identify and segment objects in complex, cluttered environments, even when they are partially hidden. It takes real-time RGB-D camera feeds (color and depth information) from sensors like Azure Kinect or Intel Realsense and outputs precise outlines of objects, including the parts that are occluded. Robotics engineers can use this to improve robot manipulation, grasping, and scene understanding in factories or warehouses.

149 stars. No commits in the last 6 months.

Use this if you need to enable a robot or an automated system to 'see' and precisely understand the full shape of individual objects in a cluttered scene, even when those objects are partially blocked by others.

Not ideal if you only need to detect objects that are fully visible, or if your application does not involve depth-sensing cameras.

robotics industrial-automation computer-vision object-manipulation scene-understanding
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

149

Forks

28

Language

Python

License

Last pushed

Jul 23, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/gist-ailab/uoais"

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