Abstract
Inspired by cognitive science, we present CREATIVEFLOW, an analogical generation framework that explicitly models analogical divergent thinking to mitigate creative homogenization in text-to-3D pipelines. Our method derives a series of meaningful yet relationally similar source-target asset pairs, each featuring distinct geometric configurations. Expert evaluations demonstrate that our framework substantially enhances creative novelty and visual fascination. This workflow and its resulting assets establish a foundational dataset and benchmark for future relation-aware 3D model training.
Keywords
Subject
Publication details
- DOI
- 10.1145/3829333.3847960
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Li, X., Zhang, S., Zhao, N., & Chen, Q. (2026). CreativeFlow: A One-to-Many Analogical Relation Transfer Method for 3D Asset Generation. https://doi.org/10.1145/3829333.3847960
MLA 9
Li, Xuechen, et al. "CreativeFlow: A One-to-Many Analogical Relation Transfer Method for 3D Asset Generation." https://doi.org/10.1145/3829333.3847960.
Chicago (author–date)
Li, Xuechen, Shuai Zhang, Nanxuan Zhao, and Qing Chen. 2026. "CreativeFlow: A One-to-Many Analogical Relation Transfer Method for 3D Asset Generation." https://doi.org/10.1145/3829333.3847960.
Harvard
Li, X., Zhang, S., Zhao, N. and Chen, Q. (2026) 'CreativeFlow: A One-to-Many Analogical Relation Transfer Method for 3D Asset Generation', doi:10.1145/3829333.3847960.
Vancouver
Li X, Zhang S, Zhao N, Chen Q. CreativeFlow: A One-to-Many Analogical Relation Transfer Method for 3D Asset Generation. doi:10.1145/3829333.3847960
IEEE
X. Li, S. Zhang, N. Zhao, and Q. Chen, "CreativeFlow: A One-to-Many Analogical Relation Transfer Method for 3D Asset Generation," doi: 10.1145/3829333.3847960.