Metraipolis › archive › dc_a0931b96f673

PhysX-CoT: Structured Physical Reasoning from a Single Image to Simulation-Ready 3D Assets — arXiv:2608.08053

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.08053
License (as archived)
CC0-1.0
Archived
2026-10-19T09:12:30.244Z
SHA-256 of the archived text
25eea9ee460487aab65d168a99f7ea4628fc0d72246d348179c54c6351aacc57
Stable URL of this page
https://metraipolis.com/documento/dc_a0931b96f673

How to cite

PhysX-CoT: Structured Physical Reasoning from a Single Image to Simulation-Ready 3D Assets — arXiv:2608.08053 — arXiv (en), https://arxiv.org/abs/2608.08053 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a0931b96f673 (Metraipolis archive dc_a0931b96f673, sha256 25eea9ee460487aab65d168a99f7ea4628fc0d72246d348179c54c6351aacc57)
BibTeX
@misc{dca0931b96f673,
  title = {PhysX-CoT: Structured Physical Reasoning from a Single Image to Simulation-Ready 3D Assets — arXiv:2608.08053},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.08053},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a0931b96f673; sha256 25eea9ee460487aab65d168a99f7ea4628fc0d72246d348179c54c6351aacc57},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08053. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Simulation-ready 3D assets are central to robotics and embodied AI. Generating them from a single image is usually framed as a vision-language model that emits a serialized asset for a decoder to turn into geometry and physical fields, leaving the image-to-3D reasoning implicit. We argue the limiting factor is this output-centric view: part placement and local shape are entangled in one global-coordinate token stream, and the intermediate physical states are never exposed for supervision, conditioning, or verification. PhysX-CoT instead casts single-image asset generation as an explicit structured physical reasoning process, an ordered and machine-parseable trajectory of part-level states covering decomposition, 2D and 3D grounding, relations, coarse geometry, and surface cues that we separately supervise, use to condition geometry, and treat as reward targets. Geometry is factorized so that 3D boxes carry placement and local codes carry shape, and CoT-aligned GRPO optimizes parse validity, grounding, geometry, placement, and physical consistency. Under a unified protocol that retrains all learned baselines on the same backbone, data, and frozen decoder, PhysX-CoT outperforms the closest full-task baseline across geometry, scale, and physical-attribute metrics. Oracle, token-matched, and state-order controls show the explicit states are functional rather than cosmetic, and in Unreal Engine~5 the generated assets parse, collide, and articulate at high validity.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-11 in cs.RO).
Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.08053 — 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 2026-10-19T09:11:58.736Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).