Metraipolis › archive › dc_c191e31ddada

GIF: Agentic Generation of Interactive and Functional Object Compositions for Robot Learning — arXiv:2609.05927

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.05927
License (as archived)
CC0-1.0
Archived
2026-10-16T15:30:42.907Z
SHA-256 of the archived text
1a518acca9fd53654d8839f7414efff9664e40d33b3170aa36e61f74f420d9a9
Stable URL of this page
https://metraipolis.com/documento/dc_c191e31ddada

How to cite

GIF: Agentic Generation of Interactive and Functional Object Compositions for Robot Learning — arXiv:2609.05927 — arXiv (en), https://arxiv.org/abs/2609.05927 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c191e31ddada (Metraipolis archive dc_c191e31ddada, sha256 1a518acca9fd53654d8839f7414efff9664e40d33b3170aa36e61f74f420d9a9)
BibTeX
@misc{dcc191e31ddada,
  title = {GIF: Agentic Generation of Interactive and Functional Object Compositions for Robot Learning — arXiv:2609.05927},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.05927},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c191e31ddada; sha256 1a518acca9fd53654d8839f7414efff9664e40d33b3170aa36e61f74f420d9a9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05927. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Robot manipulation foundation models require scalable evaluation and data generation across diverse scenarios, with simulation providing an environment for both. Automated scene generation offers a promising path, yet prior work has largely emphasized coarse-grained scene layouts rather than fine-grained functional object compositions. Motivated by this gap, we present GIF, an agentic Generation framework for Interactive and Functional object compositions. In this framework, we recast this problem as disentangled reconstruction followed by relative pose recovery. CoGen produces instance-disentangled meshes with coarse initial poses leveraging complementary strengths of 2D and 3D generative models. GPRM refines the relative pose under joint geometric and physical guidance, and a VLM verifier selects the candidate that best matches the structured specification. We further construct a benchmark spanning eight representative contact-geometry classes and compare with state-of-the-art generators; GIF improves both asset quality and relation matching, while reducing collision rate to below 1%. Finally, we synthesize data for policy learning, revealing diversity scaling in both simulation and real-world deployment.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.05927 — 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 2026-10-16T15:11:47.502Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).