从单一到多元：面向三维生成的上下文部件潜在表示

摘要

近期3D生成技术已从多视角2D渲染方法转向了利用真实数据中几何先验的3D原生潜在扩散框架。尽管取得了进展，仍存在三个关键限制：(1) 单一潜在表示无法捕捉复杂的多部件几何结构，导致细节退化；(2) 整体潜在编码忽视了部件独立性和相互关系，这对组合设计至关重要；(3) 全局条件机制缺乏细粒度可控性。受人类3D设计流程启发，我们提出了CoPart——一个部件感知的扩散框架，它将3D对象分解为上下文相关的部件潜在表示，以实现连贯的多部件生成。这一范式具有三大优势：i) 通过部件分解降低编码复杂度；ii) 支持显式的部件关系建模；iii) 实现部件级别的条件控制。我们进一步开发了一种互指导策略，用于微调预训练的扩散模型，以联合去噪部件潜在表示，确保几何一致性和基础模型先验。为了支持大规模训练，我们构建了Partverse——一个新颖的3D部件数据集，通过自动化网格分割和人工验证标注从Objaverse衍生而来。大量实验证明，CoPart在部件级编辑、关节对象生成及场景组合方面展现出卓越能力，并提供了前所未有的可控性。

English

Recent advances in 3D generation have transitioned from multi-view 2D rendering approaches to 3D-native latent diffusion frameworks that exploit geometric priors in ground truth data. Despite progress, three key limitations persist: (1) Single-latent representations fail to capture complex multi-part geometries, causing detail degradation; (2) Holistic latent coding neglects part independence and interrelationships critical for compositional design; (3) Global conditioning mechanisms lack fine-grained controllability. Inspired by human 3D design workflows, we propose CoPart - a part-aware diffusion framework that decomposes 3D objects into contextual part latents for coherent multi-part generation. This paradigm offers three advantages: i) Reduces encoding complexity through part decomposition; ii) Enables explicit part relationship modeling; iii) Supports part-level conditioning. We further develop a mutual guidance strategy to fine-tune pre-trained diffusion models for joint part latent denoising, ensuring both geometric coherence and foundation model priors. To enable large-scale training, we construct Partverse - a novel 3D part dataset derived from Objaverse through automated mesh segmentation and human-verified annotations. Extensive experiments demonstrate CoPart's superior capabilities in part-level editing, articulated object generation, and scene composition with unprecedented controllability.