RoboPhys-3D: A Comprehensive Embodied World Model Evaluation via 3D Reconstruction
RoboPhys-3D, a 3D-grounded EWM benchmark built on RoboTwin 2.0, is introduced, and Average Full Score, a hierarchical score averaging all 50 metrics for comprehensive evaluation, and RoboPhyscore, a compact task-aligned score averaging the metrics most strongly correlated with task success are introduced.
Tian-Yi Wang, Jia-Zhou Chen, Yi-Ming Xu et al.
· 1 citation