Metraipolis › archive › dc_5e32be0b39ec

Grounding Generative Verification in 3D Content — arXiv:2610.22360

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.22360
License (as archived)
CC0-1.0
Archived
2026-10-16T10:39:23.299Z
SHA-256 of the archived text
c0fe1024bd43f94ef86db96aa4c7d8a9a80437a4333186ee7f4433f64c3842de
Stable URL of this page
https://metraipolis.com/documento/dc_5e32be0b39ec

How to cite

Grounding Generative Verification in 3D Content — arXiv:2610.22360 — arXiv (en), https://arxiv.org/abs/2610.22360 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5e32be0b39ec (Metraipolis archive dc_5e32be0b39ec, sha256 c0fe1024bd43f94ef86db96aa4c7d8a9a80437a4333186ee7f4433f64c3842de)
BibTeX
@misc{dc5e32be0b39ec,
  title = {Grounding Generative Verification in 3D Content — arXiv:2610.22360},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.22360},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5e32be0b39ec; sha256 c0fe1024bd43f94ef86db96aa4c7d8a9a80437a4333186ee7f4433f64c3842de},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22360. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent advances in multimodal large language models (MLLMs) and 3D generation have expanded 3D understanding and synthesis. However, beyond visual fidelity, task-specific correctness grounded in 3D evidence remains a major challenge. We argue that building reliable 3D systems requires not only stronger generation and reasoning, but also verification feedback that identifies unmet requirements and explains their violations, allowing systems to reflect on and refine their outputs. Such feedback must integrate multi-view observations and distinguish genuine inconsistencies from projection-dependent appearances. We make three contributions. First, we introduce 3DVerifierBench, a benchmark spanning 10 tasks that evaluates decisions, rejection explanations, and responses to controlled changes in specifications and candidates. A human study reveals a 21.6 percentage-point gap between humans and the strongest tested model, GPT-6 Astra, while explanation-aware analysis exposes weaknesses in rejection reliability. Second, we analyze verification across fine-grained factual categories, exposing errors in values and target binding. We develop a scalable pipeline combining multi-view fact extraction, controlled 3D editing, and native annotations to produce 14,126 training examples with contradiction explanations and linked counterfactuals. Third, we examine how verification could support 3D generation through candidate selection and recursive refinement. In human-labeled sixteen-candidate pools, oracle selection improves complete factual success from 26.7% to 90.0%. In a separate eight-input study, human-guided recursive refinement satisfies all seven requirements for every input, compared with three under parallel Oracle@8. Together, our benchmark, analysis, and data pipeline establish a foundation for models to reflect on 3D content through reliable verification feedback.

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/2610.22360 — 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 2026-10-16T08:52:02.745Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).