用超椭球体分解3D场景，实现紧凑又精确的表示。
SuperDec: 3D Scene Decomposition with Superquadric Primitives
- 将任意物体点云分解为少量超椭球体，提升表示效率。
- 在ShapeNet训练后，在ScanNet++和Replica上验证泛化能力。
- 适用于机器人操作与可控内容生成，兼具实用与灵活性。
我们提出SuperDec，一种通过超椭球体基元分解构建紧凑3D场景表示的方法。尽管现有工作多利用几何基元生成逼真3D表示，我们则聚焦于获得紧凑而富有表现力的表示。方法上，针对单个物体进行局部求解，并借助实例分割技术扩展至完整3D场景。为此，设计了一种新架构，可高效将任意物体点云分解为一组紧凑的超椭球体。模型在ShapeNet上训练，并在从ScanNet++提取的物体实例及完整Replica场景上验证了泛化能力。最终，展示了基于超椭球体的紧凑表示在机器人任务、可控视觉内容生成与编辑等下游应用中的实用性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。