EUVIMEDEUVIMED entdecken
Crossref

SRAM: Shape-Realism Alignment Metric for No Reference 3D Shape Evaluation

Sheng Liu, Tianyu Luan, Phani Nuney, Xuelu Feng, Junsong Yuan

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (44) · 37654-37662

DOI: 10.1609/aaai.v40i44.41100 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Sheng Liu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

3D generation and reconstruction techniques have been widely used in computer games, film, and other content creation areas. As the application grows, there is a growing demand for 3D shapes that look truly realistic. Traditional evaluation methods rely on a ground truth to measure mesh fidelity. However, in many practical cases, a shape's realism does not depend on having a ground truth reference. In this work, we propose a Shape-Realism Alignment Metric that leverages a large language model (LLM) as a bridge between mesh shape information and realism evaluation. To achieve this, we adopt a mesh encoding approach that converts 3D shapes into the language token space. A dedicated realism decoder is designed to align the language model’s output with human perception of realism. Additionally, we introduce a new dataset, RealismGrading, which provides human-annotated realism scores without the need for ground truth shapes. Our dataset includes shapes generated by 16 different algorithms on over a dozen objects, making it more representative of practical 3D shape distributions. We validate our metric's performance and generalizability through k-fold cross-validation across different objects. Experimental results show that our metric correlates well with human perceptions and outperforms existing methods, and has good generalizability.

Zitieren

APA

Liu, S., Luan, T., Nuney, P., Feng, X., & Yuan, J. (2026). SRAM: Shape-Realism Alignment Metric for No Reference 3D Shape Evaluation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(44), 37654-37662. https://doi.org/10.1609/aaai.v40i44.41100

Vancouver

Liu S, Luan T, Nuney P, Feng X, Yuan J. SRAM: Shape-Realism Alignment Metric for No Reference 3D Shape Evaluation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(44):37654-37662. doi:10.1609/aaai.v40i44.41100

BibTeX
@article{Liu2026,
  author = {Liu, Sheng and Luan, Tianyu and Nuney, Phani and Feng, Xuelu and Yuan, Junsong},
  title = {SRAM: Shape-Realism Alignment Metric for No Reference 3D Shape Evaluation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {44},
  pages = {37654--37662},
  doi = {10.1609/aaai.v40i44.41100}
}
Kostenlos starten →