Reproduce “HMB-GAN: Hybrid Multi-Bézier GAN for Vector Shape Synthesis” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Elian Hugh Thiele-Evans, Binh Duong Pham, Hani Omar M Alharbi, Liibaan Aaden, Syed Umer Hasnain Zaidi, Prem Prakash Jayaraman, Muhammad Saeed, Boris Eisenbart
HMB-GAN generates closed shapes from joined Bézier segments, sharing endpoints by construction while using a loss to encourage tangent alignment. The authors compare a variational quantum circuit generator with a classical generator on CAD sketches. The quantum model records test-set MMD of 0.059 versus 0.064, with overlapping confidence intervals; the comparison does not establish a quantum-computing advantage.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.