HUG-VAS: A Hierarchical NURBS-Based Generative Model for Aortic Geometry Synthesis and Controllable Editing
HUG-VAS is the first SSM frameworks to unify NURBS parameterization, hierarchical diffusion, and DPS-based zero-shot conditional generation, enabling reconstruction and completion of vascular geometry from sparse, partial geometric priors without retraining.
Pan Du, Ming-Qi Xu, Xiao-Zhi Zhu et al.
· Computer Methods in Applied... · 0 citations