HybridSDF: Combining Deep Implicit Shapes and Geometric Primitives for 3D Shape Representation and Manipulation
This work addresses the challenge of capturing regularities in manufactured objects for 3D shape representation, though it appears incremental as it builds on existing deep implicit and geometric methods.
The paper tackled the problem of representing and manipulating 3D shapes in manufactured objects by combining deep implicit surfaces with geometric primitives, resulting in a method that effectively models both complex and regular shapes for efficient and precise manipulation.
Deep implicit surfaces excel at modeling generic shapes but do not always capture the regularities present in manufactured objects, which is something simple geometric primitives are particularly good at. In this paper, we propose a representation combining latent and explicit parameters that can be decoded into a set of deep implicit and geometric shapes that are consistent with each other. As a result, we can effectively model both complex and highly regular shapes that coexist in manufactured objects. This enables our approach to manipulate 3D shapes in an efficient and precise manner.