HMB-GAN: Hybrid Multi-B\'ezier GAN for Vector Shape Synthesis

Abstract:We explore the use of hybrid quantum-classical generative adversarial networks for synthesising CAD-ready vector geometries. Unlike prior work that operates in rasterised or single-Bézier domains, we introduce HMB-GAN (Hybrid Multi-Bézier GAN), an end-to-end differentiable generative framework that constructs closed shapes through stitched multi-segment Bézier representations with geometric continuity enforced by construction. We compare a quantum-enhanced generator with a classical generator within this architecture and evaluate them across point cloud distribution metrics and geometric shape statistics. Results show that despite faster convergence, a reduction in model parameter count, and slightly improved performance on point cloud metrics, the quantum generator suffers from excessive simulator overhead and thus classically-simulated evaluation suffers from hardware constraints. These results demonstrate the feasibility of modelling structured geometries through hybrid quantum architectures whilst highlighting contemporary hardware limitations.

7 pages, 2 figures, 3 tables. Published in the 2026 IEEE International Conference on Quantum Software (QSW)

Machine Learning (cs.LG)

arXiv:2609.21158 [cs.LG]

(or arXiv:2609.21158v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2609.21158 arXiv-issued DOI via DataCite (pending registration)

E. H. Thiele-Evans et al., "HMB-GAN: Hybrid Multi-Bézier GAN for Vector Shape Synthesis", 2026 IEEE International Conference on Quantum Software (QSW), pp. 222-228, 2026

https://doi.org/10.1109/QSW72780.2026.00033 DOI(s) linking to related resources