Metraipolis › archive › dc_4beccc4ecdf3

RoboPhys-3D: A Comprehensive Embodied World Model Evaluation via 3D Reconstruction — arXiv:2608.28718

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.28718
License (as archived): CC0-1.0
Archived: 2026-10-17T07:47:15.257Z
SHA-256 of the archived text: 32d2dbd11d5dcd59a2aae51eddf623281cf377520f02ff4dc21fdf5a8e57875b
Stable URL of this page: https://metraipolis.com/documento/dc_4beccc4ecdf3

How to cite

RoboPhys-3D: A Comprehensive Embodied World Model Evaluation via 3D Reconstruction — arXiv:2608.28718 — arXiv (en), https://arxiv.org/abs/2608.28718 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4beccc4ecdf3 (Metraipolis archive dc_4beccc4ecdf3, sha256 32d2dbd11d5dcd59a2aae51eddf623281cf377520f02ff4dc21fdf5a8e57875b)

BibTeX

@misc{dc4beccc4ecdf3,
  title = {RoboPhys-3D: A Comprehensive Embodied World Model Evaluation via 3D Reconstruction — arXiv:2608.28718},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28718},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4beccc4ecdf3; sha256 32d2dbd11d5dcd59a2aae51eddf623281cf377520f02ff4dc21fdf5a8e57875b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28718. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Video world models increasingly serve as data engines, action planners, and simulators for embodied AI, but conventional embodied world model (EWM) benchmarks lack a unified 3D-grounded protocol for establishing whether generated rollouts preserve the underlying 3D scene state or translate into executable actions. We introduce RoboPhys-3D, a 3D-grounded EWM benchmark built on RoboTwin 2.0, covering 50 manipulation tasks across four regimes, with 5,000 episodes and 25,000 multi-view ground-truth videos. A defining feature of RoboPhys-3D is that generated and ground-truth videos are processed through the same 3D reconstruction pipeline, enabling reconstruction-induced error to be distinguished from generation-induced error. The RoboPhys-3D benchmark organizes 50 complementary metrics into 18 sub-dimensions across four levels: pixel-level fidelity, 3D geometry consistency, state-level understanding, and task-level completeness. We further introduce 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. Among the four representative video world models, Cosmos 3 achieves the highest RoboPhyscore (0.6330, 92.7% of ground truth), while state- and execution-grounded metrics reveal substantial failures that perceptual and vision-language model-based judgments fail to capture. RoboPhyscore further exhibits strong agreement with human evaluation (Pearson r = 0.9761 and Spearman \r{ho} = 0.8962), demonstrating the importance of grounded, execution-aware evaluation for EWM capability.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Emerging Technologies (cs.ET); Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2608.28718 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T07:28:26.681Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).