OmniPart：基于语义解耦与结构一致性的部件感知三维生成

摘要

创建具有明确、可编辑部件结构的3D资产对于推动交互应用至关重要，然而大多数生成方法仅能产生整体形状，限制了其实用性。我们提出了OmniPart，一种新颖的部件感知3D对象生成框架，旨在实现组件间的高度语义解耦，同时保持坚固的结构一致性。OmniPart独特地将这一复杂任务分解为两个协同阶段：(1) 自回归结构规划模块生成可控、可变长度的3D部件边界框序列，关键性地由灵活的2D部件掩码引导，这些掩码允许直观地控制部件分解，而无需直接对应关系或语义标签；(2) 空间条件修正流模型，从预训练的整体3D生成器高效适配，在规划布局内同时且一致地合成所有3D部件。我们的方法支持用户定义的部件粒度、精确定位，并实现多样化的下游应用。大量实验表明，OmniPart达到了最先进的性能，为更可解释、可编辑和多功能3D内容铺平了道路。

English

The creation of 3D assets with explicit, editable part structures is crucial for advancing interactive applications, yet most generative methods produce only monolithic shapes, limiting their utility. We introduce OmniPart, a novel framework for part-aware 3D object generation designed to achieve high semantic decoupling among components while maintaining robust structural cohesion. OmniPart uniquely decouples this complex task into two synergistic stages: (1) an autoregressive structure planning module generates a controllable, variable-length sequence of 3D part bounding boxes, critically guided by flexible 2D part masks that allow for intuitive control over part decomposition without requiring direct correspondences or semantic labels; and (2) a spatially-conditioned rectified flow model, efficiently adapted from a pre-trained holistic 3D generator, synthesizes all 3D parts simultaneously and consistently within the planned layout. Our approach supports user-defined part granularity, precise localization, and enables diverse downstream applications. Extensive experiments demonstrate that OmniPart achieves state-of-the-art performance, paving the way for more interpretable, editable, and versatile 3D content.

OmniPart：基于语义解耦与结构一致性的部件感知三维生成

OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion

摘要

Support