GEM3D: GEnerative Medial Abstractions for 3D Shape Synthesis

arXiv:2402.16994v1 Announce Type: cross
Abstract: We introduce GEM3D -- a new deep, topology-aware generative model of 3D shapes. The key ingredient of our method is a neural skeleton-based representation encoding information on both shape topology and geometry. Through a denoising diffusion probabilistic model, our method first generates skeleton-based representations following the Medial Axis Transform (MAT), then generates surfaces through a skeleton-driven neural implicit formulation. The neural implicit takes into account the topological and geometric information stored in the generated skeleton …

abstract abstractions arxiv cs.ai cs.cv cs.gr cs.lg denoising diffusion encoding generative geometry information key probabilistic model representation synthesis the key through topology type