AI RESEARCH
Sketch2MinSurf: Vision-Language Guided Generation of Editable Minimal Surfaces from Hand-Drawn Sketches
arXiv CS.CV
•
ArXi:2605.20733v1 Announce Type: new Converting hand-drawn sketches into structured 3D geometries remains challenging due to the difficulty of representing non-Euclidean surfaces and maintaining topological consistency. Existing generative models such as GANs, NeRFs, and diffusion architectures often fail to produce editable manifolds directly usable in downstream design workflows.