HOC2R: Hand-Object Contact Trajectories for Human-to-Robot Motion Transfer
HOC2R: Hand-Object Contact Trajectories for Human-to-Robot Motion Transfer
This research presents HOC2R, a system that extracts hand-object contact trajectories from human videos to enable robot motion transfer.
The paper introduces HOC2R, a method combining frozen DINOv3 and SAM 2.1 features to extract hand-object contact trajectories from human videos for robot motion transfer, reporting specific accuracy improvements on a 30-task benchmark and feasibility results across six robot evaluation sequences.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Data origin
- Robot trajectoriesOpen source S2
Reported numbers
Reported accuracy
58.1%
Reported trials
View original evidence
e automation that detects, counts, and localizes visible contacts in untrimmed videos, and fixed-two localization for two-finger grippers when contact frames are known. On a 30-task point-annotated benchmark, count-aware automation improves contact-count accuracy from 58.1% to 71.4% and reduces mean localization distance from 19.81 to 10.46 pixels relative to an adapted VRB2 baseline. On seven unseen RGB-D rollouts,
Open source S3Reported accuracy
71.4%
Reported trials
View original evidence
e automation that detects, counts, and localizes visible contacts in untrimmed videos, and fixed-two localization for two-finger grippers when contact frames are known. On a 30-task point-annotated benchmark, count-aware automation improves contact-count accuracy from 58.1% to 71.4% and reduces mean localization distance from 19.81 to 10.46 pixels relative to an adapted VRB2 baseline. On seven unseen RGB-D rollouts,
Open source S3successful tasks
3
Reported trials
View original evidence
a five-task fixed-two checkpoint reduces mean localization distance from 67.67 to 27.02 pixels. Across six robot evaluation sequences, the 30-task fixed-two checkpoint produces four feasible trajectories and succeeds on three tasks, compared with two feasible trajectories and one successful task for each adapted baseline. HOC2R is competitive in the evaluated single-hand scenes, robust to the hand-color shift, and st
Open source S4
- paper: not_reported
What remains unknown
Not established in the collected evidence: Environment, Control.
Reported performance applies to the described task. It does not establish general autonomy or deployment readiness.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
arXiv:2611.08920v1 Announce Type: new Abstract: Human videos contain abundant object-manipulation demonstrations, but they do not directly provide motion cues that a robot can follow. We present HOC2R, a Hand-Object Contact trajectory extractor for Robot motion that combines frozen DINOv3 and SAM 2.1 features with learned heads for hand-object association and contact localization. HOC2R supports two modes: count-awar
Open source S2
e automation that detects, counts, and localizes visible contacts in untrimmed videos, and fixed-two localization for two-finger grippers when contact frames are known. On a 30-task point-annotated benchmark, count-aware automation improves contact-count accuracy from 58.1% to 71.4% and reduces mean localization distance from 19.81 to 10.46 pixels relative to an adapted VRB2 baseline. On seven unseen RGB-D rollouts,
Open source S3
a five-task fixed-two checkpoint reduces mean localization distance from 67.67 to 27.02 pixels. Across six robot evaluation sequences, the 30-task fixed-two checkpoint produces four feasible trajectories and succeeds on three tasks, compared with two feasible trajectories and one successful task for each adapted baseline. HOC2R is competitive in the evaluated single-hand scenes, robust to the hand-color shift, and st
Open source S4
Implications for data suppliers
RoboSignal interpretation and collection questions, not statements of buyer demand.
- Match the buyer’s robot embodiment, action space, sensors and timestamp requirements before planning collection.
- Compare the reported units and scope before using these quantities in a budget. Recording hours, sensor-hours and trajectories are different measures.
- Validate demand and acceptance criteria with a buyer before scaling. Publication, popularity and a research result do not establish a purchase commitment.
Source：arXiv Robotics — research abstracts · arxiv.org