X-Part：高保真且结构连贯的形状分解与补全
X-Part: High Fidelity And Structure Coherent Shape Decomposition And Completion
把边界框当作部件生成的提示、并注入逐点语义特征来实现语义一致的部件分解，这套「框提示 + 点特征」的条件注入方式可直接迁移到部件级补全、重拓扑与可编辑资产生成流程中。
原文依据 X-Part exploits the bounding box as prompts for the part generation and injects point-wise semantic features for meaningful decomposition.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论在部件级别生成三维形状对于网格重拓扑、UV 展开和三维打印等下游应用至关重要。然而，现有的基于部件的生成方法往往缺乏足够的可控性，并且难以获得语义上有意义的分解。为此，我们提出 X-Part，一种可控生成模型，旨在将整体三维物体分解为语义上有意义且结构连贯、几何保真度高的部件。X-Part 利用边界框作为部件生成的提示，并注入逐点语义特征以实现有意义的分解。此外，我们设计了一套可编辑流程，用于交互式部件生成。大量实验结果表明，X-Part 在部件级形状生成上取得了最优性能。这项工作为创建可用于生产、可编辑且结构合理的三维资产建立了新范式。代码将公开以支持公开研究。
英文原文摘要 963 字符
Generating 3D shapes at part level is pivotal for downstream applications such as mesh retopology, UV mapping, and 3D printing. However, existing part-based generation methods often lack sufficient controllability and suffer from poor semantically meaningful decomposition. To this end, we introduce X-Part, a controllable generative model designed to decompose a holistic 3D object into semantically meaningful and structurally coherent parts with high geometric fidelity. X-Part exploits the bounding box as prompts for the part generation and injects point-wise semantic features for meaningful decomposition. Furthermore, we design an editable pipeline for interactive part generation. Extensive experimental results show that X-Part achieves state-of-the-art performance in part-level shape generation. This work establishes a new paradigm for creating production-ready, editable, and structurally sound 3D assets. Codes will be released for public research.