X-Part可生成语义合理、结构连贯的高保真3D部件，支持交互编辑。
X-Part: high fidelity and structure coherent shape decomposition
- 用边界框作提示，结合点级语义特征实现可控分解
- 在ShapeNet等数据集上达到当前最优的部件生成效果
- 适合需要可编辑、结构完整3D资产的工业设计场景
在网格重拓扑、UV贴图和3D打印等下游应用中，基于部件的3D形状生成至关重要。然而，现有方法往往控制性不足，且分解结果缺乏语义合理性。为此，我们提出X-Part，一种可控生成模型，能够将整体3D物体分解为语义合理、结构连贯且几何保真的部件。X-Part利用边界框作为生成提示，并注入点级语义特征以实现有意义的分解。此外，我们设计了可交互编辑的生成流程。大量实验表明，X-Part在部件级形状生成任务中达到当前最优性能。本工作建立了可生产化、可编辑且结构稳定的3D资产新范式。代码将公开用于研究。
原文摘要 · Abstract (English)
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.
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。