将3D物体分解为可独立控制的部件，实现精准设计与优化。
PartSDF: Part-Based Implicit Neural Representation for Composite 3D Shape Parametrization and Optimization
- 基于部件的隐式表示，支持独立建模与控制。
- 在重建与生成任务中优于现有监督与无监督方法。
- 适合需要结构化控制的工程设计与优化场景。
精确的3D形状表示在设计、优化和仿真等工程应用中至关重要。实际工程流程需要基于部件的结构化表示，因为物体本质上是多个独立组件的组合。然而，现有方法大多整体建模或无预定义部件结构地分解形状，限制了其在真实设计任务中的适用性。本文提出PartSDF，一种监督式的隐式表示框架，显式建模具有独立可控部件的复合形状，同时保持整体一致性。得益于其简洁而创新的架构，PartSDF在重建与生成任务中超越了多种监督与无监督基线方法。我们进一步验证其作为工程应用中结构化形状先验的有效性，可在保持整体协调性的同时对单个部件进行精确控制。代码已开源：https://github.com/cvlab-epfl/PartSDF。
原文摘要 · Abstract (English)
Accurate 3D shape representation is essential in engineering applications such as design, optimization, and simulation. In practice, engineering workflows require structured, part-based representations, as objects are inherently designed as assemblies of distinct components. However, most existing methods either model shapes holistically or decompose them without predefined part structures, limiting their applicability in real-world design tasks. We propose PartSDF, a supervised implicit representation framework that explicitly models composite shapes with independent, controllable parts while maintaining shape consistency. Thanks to its simple but innovative architecture, PartSDF outperforms both supervised and unsupervised baselines in reconstruction and generation tasks. We further demonstrate its effectiveness as a structured shape prior for engineering applications, enabling precise control over individual components while preserving overall coherence. Code available at https://github.com/cvlab-epfl/PartSDF.
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。