Technology Category
Computer Vision: Representation Learning for VisionMachine Learning: Learning with ManifoldsKnowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
SuperDec: 3D Scene Decomposition with Superquadric Primitives
🤖 AI Summary
Existing 3D scene representations struggle to simultaneously achieve high geometric fidelity and strong compression efficiency. Method: This paper proposes the first end-to-end learnable, scene-wide, instance-level superquadric decomposition framework. We design a local object parameter regression network, integrate it with an instance-segmentation-guided global decomposition paradigm, and employ a hybrid training strategy combining ShapeNet supervision with cross-domain generalization on ScanNet++ and Replica. Contribution/Results: Our approach establishes the first differentiable, instance-aligned mapping from raw point clouds to superquadric parameters. It significantly improves reconstruction accuracy and cross-dataset generalization. Quantitatively, it achieves state-of-the-art geometric reconstruction quality on both ScanNet++ and Replica. The learned compact superquadric representations effectively support downstream applications including robotic grasp planning and controllable 3D editing.
Technology Category
Application Category
📝 Abstract
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.
Problem
Research questions and friction points this paper is trying to address.
Decomposing 3D scenes into superquadric primitives
Creating compact and expressive 3D representations
Enabling applications in robotics and content generation
Innovation
Methods, ideas, or system contributions that make the work stand out.
Decompose 3D scenes into superquadric primitives
Use instance segmentation for scalable solutions
Compact superquadric representation for diverse applications
🔎 Similar Papers
No similar papers found.
