发表机构
University of New South Wales; Australian National University; Nanjing University; Southwestern University of Finance and Economics; University of Technology Sydney（新南威尔士大学; 澳大利亚国立大学; 南京大学; 西南财经大学; 悉尼科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对三维部件分解的结构尺度不匹配问题，提出Hi-TOPS层次化拓扑感知评分先验，结合Flow-Freeze场等技术实现稳定可编辑的部件分解，无需语义监督或二维基础先验。
AI 中文摘要
精确的三维部件分解要求将形状分离为具有精确边界的结构上有意义的组件，同时保留关节接缝和薄附件。现有方法常存在结构尺度不匹配问题：分离的几何证据在中尺度最可靠，但许多流程要么过于全局而无法尊重关节，要么过于局部而对噪声不鲁棒。我们提出Hi-TOPS，一种层次化拓扑感知评分先验，它将互补的内在线索聚合到多分辨率的Flow-Freeze场中。Flow区域为基元覆盖提供可扩展支持，Freeze区域限制关节和薄结构附近的生长。随后，TSDF引导的体-表面超二次拟合器捕获主导核心和残余表面结构，接着进行SQ到网格的分配以得到连通、边界对齐的部件。在各种基准测试中，Hi-TOPS无需语义监督或二维基础先验即可提供稳定、可编辑的分解结果。
英文摘要
Accurate 3D part decomposition requires separating shapes into structurally meaningful components with precise boundaries while preserving articulation seams and thin attachments. Existing approaches often suffer from a structural-scale mismatch: geometric evidence for separation is most reliable at the meso scale, yet many pipelines operate either too globally to respect joints or too locally to remain robust to noise. We propose Hi-TOPS, a Hierarchical Topology-aware Scoring Prior that aggregates complementary intrinsic cues into a multi-resolution Flow-Freeze field. Flow regions provide expandable support for primitive coverage, while Freeze regions restrict growth near articulations and thin structures. A TSDF-guided body-surface superquadric fitter then captures dominant cores and residual surface structures, followed by SQ-to-mesh assignment for connected, boundary-aligned parts. Across diverse benchmarks, Hi-TOPS delivers stable, editable decompositions without semantic supervision or 2D foundation priors.
