让3D生成模型同时完成拼装与补全，提升复杂缺失场景下的装配精度。
CRAG: Can 3D Generative Models Help 3D Assembly?
- 将拼装与生成联合建模，利用结构先验和整体形状上下文互相增强。
- 在含缺失部件的野外物体上实现领先性能，支持多变零件数与几何形态。
- 适合需要补全与智能拼装的3D重建、设计辅助等应用场景。
现有3D拼装方法将问题视为纯位姿估计，通过刚性变换重组观测部件。而人类拼装自然结合了结构推理与整体形状推断。受此启发，我们重新将3D拼装定义为拼装与生成的联合问题。二者相互促进：拼装提供部件级结构先验用于生成，生成注入整体形状上下文以解决拼装歧义。不同于以往无法合成缺失几何的方法，我们提出CRAG，能同步生成合理完整形状并预测输入部件的位姿。大量实验表明，该方法在具多样几何、不同部件数量及缺失部件的野外物体上均达到当前最优表现。
原文摘要 · Abstract (English)
Most existing 3D assembly methods treat the problem as pure pose estimation, rearranging observed parts via rigid transformations. In contrast, human assembly naturally couples structural reasoning with holistic shape inference. Inspired by this intuition, we reformulate 3D assembly as a joint problem of assembly and generation. We show that these two processes are mutually reinforcing: assembly provides part-level structural priors for generation, while generation injects holistic shape context that resolves ambiguities in assembly. Unlike prior methods that cannot synthesize missing geometry, we propose CRAG, which simultaneously generates plausible complete shapes and predicts poses for input parts. Extensive experiments demonstrate state-of-the-art performance across in-the-wild objects with diverse geometries, varying part counts, and missing pieces. Project Page: https://ai4ce.github.io/CRAG/
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。