EUVIMEDDécouvrir EUVIMED
Open access · CC BY-NC-SA 4.0

Creating LEGO Figurines from Single Images

Jiahao Ge, Mingjun Zhou, Wenrui Bao, Hao Xu, Chi-Wing Fu

ACM Transactions on Graphics · 2024-07-19 · 43 (4) · 1-16

DOI: 10.1145/3658167 ↗

At a glance

Journal article in ACM Transactions on Graphics, published online on 2024-07-19. Written by Jiahao Ge and 4 co-authors. Cited 6 times so far (Crossref); 55 references. The full text is freely available (open access, CC BY-NC-SA 4.0). Funded by: The Research Grants Council of the Hong Kong Special Administrative Region.

RésuméRéférences bibliographiquesCiteRelated studies

Abstract (original language)

This paper presents a computational pipeline for creating personalized, physical LEGO ®1 figurines from user-input portrait photos. The generated figurine is an assembly of coherently-connected LEGO ® bricks detailed with uv-printed decals, capturing prominent features such as hairstyle, clothing style, and garment color, and also intricate details such as logos, text, and patterns. This task is non-trivial, due to the substantial domain gap between unconstrained user photos and the stylistically-consistent LEGO ® figurine models. To ensure assemble-ability by LEGO ® bricks while capturing prominent features and intricate details, we design a three-stage pipeline: (i) we formulate a CLIP-guided retrieval approach to connect the domains of user photos and LEGO ® figurines, then output physically-assemble-able LEGO ® figurines with decals excluded; (ii) we then synthesize decals on the figurines via a symmetric U-Nets architecture conditioned on appearance features extracted from user photos; and (iii) we next reproject and uv-print the decals on associated LEGO ® bricks for physical model production. We evaluate the effectiveness of our method against eight hundred expert-designed figurines, using a comprehensive set of metrics, which include a novel GPT-4V-based evaluation metric, demonstrating superior performance of our method in visual quality and resemblance to input photos. Also, we show our method's robustness by generating LEGO ® figurines from diverse inputs and physically fabricating and assembling several of them.

Funding

  • The Research Grants Council of the Hong Kong Special Administrative Region

Cite

APA

Ge, J., Zhou, M., Bao, W., Xu, H., & Fu, C. (2024). Creating LEGO Figurines from Single Images. ACM Transactions on Graphics, 43(4), 1-16. https://doi.org/10.1145/3658167

Vancouver

Ge J, Zhou M, Bao W, Xu H, Fu C. Creating LEGO Figurines from Single Images. ACM Transactions on Graphics. 2024;43(4):1-16. doi:10.1145/3658167

BibTeX
@article{Ge2024,
  author = {Ge, Jiahao and Zhou, Mingjun and Bao, Wenrui and Xu, Hao and Fu, Chi-Wing},
  title = {Creating LEGO Figurines from Single Images},
  journal = {ACM Transactions on Graphics},
  year = {2024},
  volume = {43},
  number = {4},
  pages = {1--16},
  doi = {10.1145/3658167}
}
Start for free →