Rank3DGAN: Semantic Mesh Generation Using Relative Attributes


  • Yassir Saquil University of Bath
  • Qun-Ce Xu University of Bath
  • Yong-Liang Yang University of Bath
  • Peter Hall University of Bath




In this paper, we investigate a novel problem of using generative adversarial networks in the task of 3D shape generation according to semantic attributes. Recent works map 3D shapes into 2D parameter domain, which enables training Generative Adversarial Networks (GANs) for 3D shape generation task. We extend these architectures to the conditional setting, where we generate 3D shapes with respect to subjective attributes defined by the user. Given pairwise comparisons of 3D shapes, our model performs two tasks: it learns a generative model with a controlled latent space, and a ranking function for the 3D shapes based on their multi-chart representation in 2D. The capability of the model is demonstrated with experiments on HumanShape, Basel Face Model and reconstructed 3D CUB datasets. We also present various applications that benefit from our model, such as multi-attribute exploration, mesh editing, and mesh attribute transfer.




How to Cite

Saquil, Y., Xu, Q.-C., Yang, Y.-L., & Hall, P. (2020). Rank3DGAN: Semantic Mesh Generation Using Relative Attributes. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 5586-5594. https://doi.org/10.1609/aaai.v34i04.6011



AAAI Technical Track: Machine Learning