Metraipolis › archive › dc_b6fb104f19b1

ESG: Generating Physically Consistent Dynamic 3D Scenes from Text Descriptions — arXiv:2609.15392

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.15392
License (as archived): CC0-1.0
Archived: 2026-10-16T01:53:45.919Z
SHA-256 of the archived text: 6ca0e1d07235fe23615990256b7e83f0780f4bf5967125d2eb4820facacd5fd7
Stable URL of this page: https://metraipolis.com/documento/dc_b6fb104f19b1

How to cite

ESG: Generating Physically Consistent Dynamic 3D Scenes from Text Descriptions — arXiv:2609.15392 — arXiv (en), https://arxiv.org/abs/2609.15392 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b6fb104f19b1 (Metraipolis archive dc_b6fb104f19b1, sha256 6ca0e1d07235fe23615990256b7e83f0780f4bf5967125d2eb4820facacd5fd7)

BibTeX

@misc{dcb6fb104f19b1,
  title = {ESG: Generating Physically Consistent Dynamic 3D Scenes from Text Descriptions — arXiv:2609.15392},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.15392},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b6fb104f19b1; sha256 6ca0e1d07235fe23615990256b7e83f0780f4bf5967125d2eb4820facacd5fd7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15392. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent progress in image and 3D scene generation has enabled increasingly realistic static environments, yet most methods remain confined to such static configurations. Generating dynamic scenes from natural language is fundamentally challenging: it requires joint reasoning over scene structure, temporal evolution, and physical feasibility, while ensuring reliable execution in modern physics engines. We present a unified framework for generating physically consistent dynamic 3D scenes from text, with outputs directly executable in Unreal Engine. Central to our approach is the \emph{Evolutive Scene Graph} (ESG), which specifies entities with physical attributes, spatial relations, and event-driven timelines in a machine-checkable form. Given a prompt, a large language model constructs and validates a complete ESG; spatial layouts are grounded via energy-minimized gradient optimization; timeline-constrained physical parameters are then optimized through differentiable simulation to satisfy user-specified events; and the resulting scene is compiled into an engine-executable class. Experiments on 10 scenes across three complexity levels show that our method achieves $16.4/18$ mean event completion, outperforming Scene Language, the strongest engine-executable baseline (SimWorld), and our ablation without physical optimization by a clear margin in event completion and parameter accuracy.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CV).
Categorie arXiv: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.15392 — 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 2026-10-16T01:25:23.743Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).