SuperDec: 3D Scene Decomposition with Superquadric Primitives
This provides a compact representation method for 3D scenes that benefits robotics and content generation applications, though it appears incremental by building on existing primitive-based approaches.
The paper tackles the problem of creating compact 3D scene representations by decomposing them into superquadric primitives, achieving generalization from ShapeNet training to ScanNet++ and Replica datasets while demonstrating utility for robotic tasks and visual content editing.
We present SuperDec, an approach for creating compact 3D scene representations via decomposition into superquadric primitives. While most recent works leverage geometric primitives to obtain photorealistic 3D scene representations, we propose to leverage them to obtain a compact yet expressive representation. We propose to solve the problem locally on individual objects and leverage the capabilities of instance segmentation methods to scale our solution to full 3D scenes. In doing that, we design a new architecture which efficiently decompose point clouds of arbitrary objects in a compact set of superquadrics. We train our architecture on ShapeNet and we prove its generalization capabilities on object instances extracted from the ScanNet++ dataset as well as on full Replica scenes. Finally, we show how a compact representation based on superquadrics can be useful for a diverse range of downstream applications, including robotic tasks and controllable visual content generation and editing.