Metraipolis › archive › dc_460adcb177fb

EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling — arXiv:2610.02298

Source
arXiv
Original
https://arxiv.org/abs/2610.02298
License (as archived)
CC0-1.0
Archived
2026-10-05T22:49:53.455Z
SHA-256 of the archived text
74604da8c8e925b0bd510eafbd1f4c988bf4325c007012a188e5bc8903a09e94
Stable URL of this page
https://metraipolis.com/documento/dc_460adcb177fb

How to cite

EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling — arXiv:2610.02298 — arXiv, https://arxiv.org/abs/2610.02298 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_460adcb177fb (Metraipolis archive dc_460adcb177fb, sha256 74604da8c8e925b0bd510eafbd1f4c988bf4325c007012a188e5bc8903a09e94)
BibTeX
@misc{dc460adcb177fb,
  title = {EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling — arXiv:2610.02298},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.02298},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_460adcb177fb; sha256 74604da8c8e925b0bd510eafbd1f4c988bf4325c007012a188e5bc8903a09e94},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02298. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

3D editing methods are usually tested on a single edit, yet an asset is built through a long sequence of revisions, each of which must implement the requested change while leaving everything else unchanged. We introduce EditHero, to our knowledge the first benchmark for long-horizon, part-level 3D editing, with natural-language instructions and target images for both geometry and texture. A deterministic assembly engine produces the exact target after every edit, and every sequence is reviewed by hand. We use EditHero to compare 2 opposite approaches to 3D editing. Non-agentic methods operate top down, regenerating the object from a learned 3D representation and inferring what to keep. In contrast, LLM/VLM agents operate bottom up, editing through code that inspects the mesh and rewrites only the parts required by instructions. The non-agentic methods often miss the requested change and disturb regions that should stay fixed. Most LLMs follow instructions more closely, and all of them preserve the unedited parts better, but each of their edits takes minutes. We will release the engine and the edit sequences to support research on reliable iterative 3D editing.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Graphics (cs.GR).
Pagina del lavoro: https://arxiv.org/abs/2610.02298 — 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 2026-10-05T22:45:55.735Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).