🧪 Test?View on arXiv
STATERA: Hidden Mass Estimation via Zero-Shot Sim-to-Real Kinematics using Frozen Temporal Tubelets
Author1, Author2, Author3, Author4, Author5
sim-to-realkinematicshidden mass estimationvideo analysis
2610.00003
Builder Relevance
1h ago70%
Abstract
This paper presents STATERA, a method for estimating the center-of-mass of opaque, asymmetric rigid bodies from monocular video, improving the accuracy of hidden mass estimation.
Reality Card
Core Claim
STATERA improves normalized center-of-mass error from 41.7% to 25.2% in simulation and enhances physics capture from 2.6% to 41.0% in zero-shot sim-to-real transfer.
Method / Result
Normalized CoM error improved from 41.7% to 25.2%.
Limitations
The method's performance may vary due to the trade-off in supervision between phase-aware and phase-agnostic targets.
Paper to code
Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.
No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.