showlab/afformer

Affordance Grounding from Demonstration Video to Target Image (CVPR 2023)

23
/ 100
Experimental

This tool helps researchers and developers working on robotic manipulation and human-computer interaction to identify how objects can be used. It takes a demonstration video of a task and a target image of a similar object, then highlights the 'actionable' parts of the object in the target image. This helps anyone developing assistive robots or smart tools understand object affordances.

No commits in the last 6 months.

Use this if you need to program robots to interact with novel objects based on human demonstrations, or analyze how humans interact with tools.

Not ideal if you are looking for a general-purpose object detection tool or if your primary interest is not in object affordances or robotic task learning.

robotics human-robot-interaction object-affordance activity-recognition computer-vision
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 7 / 25

How are scores calculated?

Stars

46

Forks

3

Language

Python

License

Last pushed

Jul 26, 2024

Commits (30d)

0

Get this data via API

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

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