SceneGenesis: 3D Scene Synthesis via Semantic Structural Priors and Mesh-Guided Video-Geometry Fusion
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (16) · 13305-13313
DOI: 10.1609/aaai.v40i16.38333 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yueming Zhao und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Generating high-quality, controllable, and structurally consistent 3D scenes in complex multi-object environments remains a fundamental challenge. We present SceneGenesis, a unified framework that synthesizes 3D scenes by combining semantic structural priors with mesh-guided video–geometry fusion. SceneGenesis first employs large language models to convert textual descriptions into category-aware object specifications, which are transformed into structured meshes using procedural approximations and pretrained asset generators, enabling precise layout control and scalable scene construction. To obtain rich and style-controllable appearances, SceneGenesis generates multi-view video representations conditioned on the initialized structure. A mesh-guided video–geometry fusion module then consolidates video evidence with mesh priors through mesh-conditioned fragment initialization, progressive geometric refinement, and structure-aware optimization, substantially improving global geometric fidelity and visual realism. Experiments demonstrate that SceneGenesis supports flexible style variation and object-level editing while achieving strong controllability, scalability, and structural quality.
Zitieren
APA
Zhao, Y., Yang, H., & Huang, D. (2026). SceneGenesis: 3D Scene Synthesis via Semantic Structural Priors and Mesh-Guided Video-Geometry Fusion. Proceedings of the AAAI Conference on Artificial Intelligence, 40(16), 13305-13313. https://doi.org/10.1609/aaai.v40i16.38333
Vancouver
Zhao Y, Yang H, Huang D. SceneGenesis: 3D Scene Synthesis via Semantic Structural Priors and Mesh-Guided Video-Geometry Fusion. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(16):13305-13313. doi:10.1609/aaai.v40i16.38333
BibTeX
@article{Zhao2026,
author = {Zhao, Yueming and Yang, Hongyu and Huang, Di},
title = {SceneGenesis: 3D Scene Synthesis via Semantic Structural Priors and Mesh-Guided Video-Geometry Fusion},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {16},
pages = {13305--13313},
doi = {10.1609/aaai.v40i16.38333}
}
EUVIMED