Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[CVPR 2023] Official repository for downloading, processing, visualizing, and training models on the ARCTIC dataset.
| Date | Stars |
|---|---|
| 2026-07-24 | 493 |
| 2026-07-25 | 493 |
| 2026-07-28 | 495 |
| 2026-07-30 | 495 |
| 2026-08-06 | 495 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
## ARCTIC 🥶: A Dataset for Dexterous Bimanual Hand-Object Manipulation
<p align="center">
<img src="docs/static/arctic-logo.svg" alt="Image" width="600" height="100" />
</p>
[ [Project Page](https://arctic.is.tue.mpg.de) ]
[ [Paper](https://download.is.tue.mpg.de/arctic/arctic_april_24.pdf) ]
[ [Video](https://www.youtube.com/watch?v=bvMm8gfFbZ8) ]
[ [Register ARCTIC Account](https://arctic.is.tue.mpg.de/register.php) ]
[ [ECCV'24 Competition](https://hands-workshop.org/challenge2024.html) ]
[ [Leaderboard](docs/leaderboard.md) ]
<p align="center">
<img src="docs/static/teaser.jpeg" alt="Image" width="100%"/>
</p>
This is a repository for preprocessing, splitting, visualizing, and rendering (RGB, depth, segmentation masks) the ARCTIC dataset.
Further, here, we provide code to reproduce our baseline models in our CVPR 2023 paper (Vancouver, British Columbia 🇨🇦) and developing custom models.
Our dataset contains heavily dexterous motion:
<p align="center">
<img src="./docs/static/dexterous.gif" alt="Image" width="100%"/>
</p>
### News
> ✨3DV 2026: Looking for hand scans data? PALM is a large-scale dataset containing high-quality 13k registered 3dMD hand scans of 263 subjects and 90k calibrated multiview RGB images. See [PALM](https://github.com/facebookresearch/PALM) for details.
>
> <p align="center">
> <img src="https://github.com/facebookresearch/PALM/blob/main/docs/static/dataset-teaser.jpg" alt="PALM Teaser" width="80%"/>
> </p>
- 2024.11.27: Want to buy objects in real life? See [`docs/purchase.md`](docs/purchase.md)
- 2024.07.07: We host HANDS workshop at ECCV'24 to reconstruct hands and objects in ARCTIC without template. Join us [here](https://hands-workshop.org/challenge2024.html)
- 2023.12.20: MoCap can be downloaded now! See download [instructions](docs/data/README.md) and [visualization](docs/data/visualize.md).
- 2023.09.11: [ARCTIC leaderboard](https://arctic-leaderboard.is.tuebingen.mpg.de/) online!
- 2023.06.16: ICCV ARCTIC [challenge](https://sites.google.com/view/hands2023/home) starts!
- 2023.05.04: ARCTIC dataset with code for dataloaders, visualizers, models is officially announced (version 1.0)!
- 2023.03.25: ARCTIC ☃️ dataset (version 0.1) is available! 🎉
Invited talks/posters at CVPR2023:
- [4D-HOI workshop: Keynote](https://4dhoi.github.io/)
- [Ego4D + EPIC workshop: Oral presentation](https://ego4d-data.org/workshops/cvpr23)
- [Rhobin workshop: Poster](https://rhobin-challenge.github.io/schedule.html)
- [3D scene understanding: Oral presentation](https://scene-understanding.com)
### Why use ARCTIC?
Summary on dataset:
- It contains 2.1M high-resolution images paired with annotated frames, enabling large-scale machine learning.
- Images are from 8x 3rd-person views and 1x egocentric view (for mixed-reality setting).
- It includes 3D groundtruth for SMPL-X, MANO, articulated objects.
- It is captured in a MoCap setup using 54 high-end Vicon cameras.
- It features highly dexterous bimanual manipulation motion (beyond quasi-static grasping).
Potential tasks with ARCTIC:
- Template-free bimanual [hand-object reconstruction](https://github.com/zc-alexfan/hold)
- Generating [hand grasp](https://korrawe.github.io/HALO/HALO.html) or [motion](https://github.com/cghezhang/ManipNet) with articulated objects
- Generating [full-body grasp](https://grab.is.tue.mpg.de/) or [motion](https://goal.is.tue.mpg.de/) with articulated objects
- Benchmarking performance of articulated object pose estimators from [depth images](https://articulated-pose.github.io/) with human in the scene
- Studying our [NEW tasks](https://download.is.tue.mpg.de/arctic/arctic_april_24.pdf) of consistent motion reconstruction and interaction field estimation
- Studying egocentric hand-object reconstruction
- Reconstructing [full-body with hands and articulated objects](https://3dlg-hcvc.github.io/3dhoi/) from RGB images
Check out our [project page](https://arctic.is.tue.mpg.de) for more details.
### ThirdExcerpt of 9,681 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:d2f2f9d6164437ce, topic:computer-vision, topic:pose-estimation, topic:3d-reconstruction
matched fp:d2f2f9d6164437ce, topic:awesome, topic:awesome-list