Metraipolis › archive › dc_c19286959c1d

RFW-A: Agentic Procedural Generation of 400K Articulated Assets over 500 Categories — arXiv:2610.40333

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.40333
License (as archived): CC0-1.0
Archived: 2026-11-01T02:42:23.901Z
SHA-256 of the archived text: d5657ca01078a2c3906004c509ecabcd0a3c80b9fc60c09ef95ebf288ff0c6e2
Stable URL of this page: https://metraipolis.com/documento/dc_c19286959c1d

How to cite

RFW-A: Agentic Procedural Generation of 400K Articulated Assets over 500 Categories — arXiv:2610.40333 — arXiv (en), https://arxiv.org/abs/2610.40333 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c19286959c1d (Metraipolis archive dc_c19286959c1d, sha256 d5657ca01078a2c3906004c509ecabcd0a3c80b9fc60c09ef95ebf288ff0c6e2)

BibTeX

@misc{dcc19286959c1d,
  title = {RFW-A: Agentic Procedural Generation of 400K Articulated Assets over 500 Categories — arXiv:2610.40333},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40333},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c19286959c1d; sha256 d5657ca01078a2c3906004c509ecabcd0a3c80b9fc60c09ef95ebf288ff0c6e2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40333. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

High-quality articulated assets are essential for embodied perception, simulation, and manipulation, yet constructing them at scale remains difficult. Manual annotation and procedural modeling require substantial human effort. Recent agentic systems automate asset construction through program synthesis, but repeat costly reasoning and refinement for every new asset. Our key observation is that assets within a category can share construction logic despite variations in structure and appearance. Agentic synthesis and procedural generation are therefore complementary: agents can construct reusable programs, while procedural execution reuses the resulting logic across many samples. We therefore present RFW-A, which combines the two in a new articulated-asset generation paradigm. Starting from existing articulated programs, RFW-A organizes reusable components and their dependencies into category-level generators. Agents test and refine these generators across sampled configurations and motion states. Once constructed and validated, the generators produce diverse assets through procedural execution with no further model calls or token charges. The estimated API cost of generator authoring averages $10.62, amortizing to $0.05 per asset over 200 assets, versus $1.24 for the sampled per-asset agentic synthesis baseline. Using RFW-A, we built RFW-A-400K, containing over 400K sim-ready articulated assets across more than 500 categories. Experiments show high structural and kinematic validity and stable execution across physics simulators. Beyond asset validity, training with RFW-A-400K improves part-level articulation estimation on seen and unseen categories, while policies trained in simulation with retrieved and program-edited assets transfer zero-shot to real articulated objects.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.40333 — 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 2026-11-01T02:16:43.982Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).