SPAGHETTI: Editing Implicit Shapes Through Part Aware Generation
This addresses the problem of 3D shape modeling and editing for users in computer graphics and AI, offering a novel approach but appearing incremental as it builds on existing neural implicit field techniques.
The paper tackles the challenge of editing neural implicit 3D shapes by introducing SPAGHETTI, a method that enables manipulation through transforming, interpolating, and combining shape segments without explicit part supervision, achieving part-level control in a generative framework.
Neural implicit fields are quickly emerging as an attractive representation for learning based techniques. However, adopting them for 3D shape modeling and editing is challenging. We introduce a method for $\mathbf{E}$diting $\mathbf{I}$mplicit $\mathbf{S}$hapes $\mathbf{T}$hrough $\mathbf{P}$art $\mathbf{A}$ware $\mathbf{G}$enera$\mathbf{T}$ion, permuted in short as SPAGHETTI. Our architecture allows for manipulation of implicit shapes by means of transforming, interpolating and combining shape segments together, without requiring explicit part supervision. SPAGHETTI disentangles shape part representation into extrinsic and intrinsic geometric information. This characteristic enables a generative framework with part-level control. The modeling capabilities of SPAGHETTI are demonstrated using an interactive graphical interface, where users can directly edit neural implicit shapes.