Metraipolis › archive › dc_137fa03aeb6f

HMB-GAN: Hybrid Multi-Bézier GAN for Vector Shape Synthesis — arXiv:2609.21158

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.21158
License (as archived): CC0-1.0
Archived: 2026-10-10T01:44:47.326Z
SHA-256 of the archived text: 88c78c318a6dac551fef123e2fa72b9112cee02b1f4967df8e638b4299d074bc
Stable URL of this page: https://metraipolis.com/documento/dc_137fa03aeb6f

How to cite

HMB-GAN: Hybrid Multi-Bézier GAN for Vector Shape Synthesis — arXiv:2609.21158 — arXiv (en), https://arxiv.org/abs/2609.21158 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_137fa03aeb6f (Metraipolis archive dc_137fa03aeb6f, sha256 88c78c318a6dac551fef123e2fa72b9112cee02b1f4967df8e638b4299d074bc)

BibTeX

@misc{dc137fa03aeb6f,
  title = {HMB-GAN: Hybrid Multi-Bézier GAN for Vector Shape Synthesis — arXiv:2609.21158},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.21158},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_137fa03aeb6f; sha256 88c78c318a6dac551fef123e2fa72b9112cee02b1f4967df8e638b4299d074bc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21158. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.21158 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-10T01:14:16.613Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).