zc-alexfan/arctic

[CVPR 2023] Official repository for downloading, processing, visualizing, and training models on the ARCTIC dataset.

49
/ 100
Emerging

This project provides a comprehensive resource for researchers and engineers working on computer vision problems involving human-object interaction. It offers tools to download, process, visualize, and train models using the ARCTIC dataset, which contains high-resolution images and 3D ground truth data of people performing complex bimanual manipulations with various objects. This is primarily for researchers and developers in fields like robotics, computer graphics, and human-computer interaction.

453 stars.

Use this if you are developing or evaluating models for understanding or generating realistic hand-object interactions, particularly those involving complex bimanual actions.

Not ideal if you are looking for a pre-trained, off-the-shelf solution for simple object recognition or single-hand grasping.

robotics computer-vision human-computer-interaction motion-synthesis 3D-reconstruction
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

453

Forks

29

Language

Python

License

Last pushed

Mar 04, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/zc-alexfan/arctic"

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