ARCTIC 🥶: A Dataset for Dexterous Bimanual Hand-Object Manipulation

• • [Video
  • [Register ARCTIC Account

• News

  • Ego4D + EPIC workshop: Oral presentation
  • here
  • Rhobin workshop: Poster
  • challenge
  • ARCTIC leaderboard
  • 4D-HOI workshop: Keynote

• Projects that use ARCTIC

  • Mitigating Perspective Distortion-induced Shape Ambiguity in Image Crops
  • SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation
  • InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusion
  • Get a Grip: Reconstructing Hand-Object Stable Grasps in Egocentric Videos
  • ArtiGrasp: Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulation
  • Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interaction
  • 3D Hand Pose Estimation in Egocentric Images in the Wild
  • Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects

• Star History

  • ![Star History Chart - history.com/#zc-alexfan/arctic&Date)

• Why use ARCTIC?

  • full-body with hands and articulated objects
  • NEW tasks
  • hand-object reconstruction
  • hand grasp
  • full-body grasp
  • depth images

• Third-party ARCTIC resources

  • Text description
  • Stable grasp
  • URDFs

• Citation

  • aitviewer

• Acknowledgments

  • Tsvetelina Alexiadis (TA) - Claude Passy](https://is.mpg.de/person/jpassy), [Valkyrie Felso](https://is.mpg.de/person/vfelso) for evaluation server. We also thank [Adrian Spurr](https://ait.ethz.ch/people/spurra/) and [Xu Chen](https://ait.ethz.ch/people/xu/) for insightful discussion. OT and DT were supported by the German Federal Ministry of Education and Research (BMBF): Tübingen AI Center, FKZ: 01IS18039B".