HOC2R: Hand-Object Contact Trajectories for Human-to-Robot Motion Transfer
cs.RO
Submitted: 2026-11-06
Updated: 2026-11-06
Code: https://github.com/liszzzzt/HOC2R
Terminology
Sources
- ContactFlow: A video action conditioning that transfers across embodiments
- SAM 2: Segment Anything in Images and Videos
- Hand-centric Human-to-Robot Trajectory Transfer from Video Demonstrations via Object Category-agnostic Temporal Localization
- DINOv3
- Human2Robot: Learning Robot Actions from Paired Human-Robot Videos
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation