Metraipolis › archive › dc_cdb1f30656cf
LEGO-Anything: Coding Agents for 3D Scene Reconstruction — arXiv:2609.36380
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36380
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T18:38:06.934Z
- SHA-256 of the archived text
cf81b7d8f8790724d5e6cdd9993a8e341533f94bae2079efc374e4e32c93f6a5- Stable URL of this page
https://metraipolis.com/documento/dc_cdb1f30656cf
How to cite
LEGO-Anything: Coding Agents for 3D Scene Reconstruction — arXiv:2609.36380 — arXiv (en), https://arxiv.org/abs/2609.36380 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cdb1f30656cf (Metraipolis archive dc_cdb1f30656cf, sha256 cf81b7d8f8790724d5e6cdd9993a8e341533f94bae2079efc374e4e32c93f6a5)
BibTeX
@misc{dccdb1f30656cf,
title = {LEGO-Anything: Coding Agents for 3D Scene Reconstruction — arXiv:2609.36380},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36380},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cdb1f30656cf; sha256 cf81b7d8f8790724d5e6cdd9993a8e341533f94bae2079efc374e4e32c93f6a5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36380. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
A 3D scene reconstructed from a single image is most useful when represented not as a rendering or a fixed 3D output, but as an explicit scene program whose execution yields a scene that can be inspected, edited, and queried. We present LEGO-Anything, an Image-to-Code framework in which a coding agent iteratively writes and executes Blender code, inspects scenes and renderings, and revises the program. To evaluate end-to-end scene recovery, we introduce LEGO-Bench, a simulator-grounded benchmark with 208 images from 104 diverse indoor and outdoor scenes. LEGO-Bench separately scores artifact validity, visible-surface geometry, and rendered appearance. Its simulator-grounded design enables extensibility and precise automatic evaluation. Among evaluated agents, GPT-6-astra achieves the strongest overall results, with 53.4% indoor and 39.6% outdoor scores, yet substantial gaps remain between delivering valid scene artifacts and faithfully recovering scene geometry and appearance. Analysis of agent construction trajectories reveals three recurring issues: weak scene initialization, regressive edits during iteration, and unreliable self-evaluation. These findings motivate LEGO-Plugin, a training-free harness plugin for more controlled iterative scene construction, which improves all six evaluated models, with relative gains of up to 62.7% in overall score. Finally, we test whether reconstructed scenes can represent natural images and support vision tasks. In LEGO-World, we derive object detections, instance masks, and relative depth as deterministic queries on scenes reconstructed by GPT-6-astra. These readouts show non-trivial performance across all three tasks but fall well short of specialized vision models, suggesting that program-constructed scenes from current coding agents are a promising but not yet sufficiently precise representation of natural images. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.36380 — 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 2026-10-07T18:04:24.691Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).