arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2607.01205cs.CV
收藏

Linkify: 从接口增强的装配图中学习

Linkify: Learning from Interface-Augmented Assembly Graphs

Iowa State University(爱荷华州立大学);Autodesk Research(Autodesk研究院)

Anushrut Jignasu, Daniele Grandi

AI总结:

提出Linkify框架,通过接口增强的装配图学习部件间几何信息,实现机械装配中的上下文感知部件检索,采用图注意力网络解决掩码部件预测任务。

摘要:

我们提出了Linkify,一个从接口增强的装配图中学习的框架,以实现机械装配中的上下文感知部件检索。虽然最近用于CAD的生成式AI方法主要集中在孤立部件或整体装配上,但部件之间实现功能的接口处的丰富几何信息仍未得到充分探索。我们通过重新计算Fusion 360 Gallery Assembly数据集的高保真接口几何形状,纠正缺失和错误的接触,并生成局部接触区域的点云表示来填补这一空白。利用这些数据,我们构建了装配图,其中节点编码部件几何形状,边通过预训练的点云编码器编码接口几何形状。在此表示之上,我们训练了一个基于GATv2的图注意力网络来解决掩码部件预测任务:给定一个缺少一个部件的装配体,模型从大量几何聚类部件词汇中预测缺失组件的类别,从而近似一个真实的部件检索场景。与在聚合节点特征上操作的逻辑回归和k近邻等非图基线相比,Linkify实现了更高的Top-K准确率和F1分数。关于图连通性、边属性和注意力机制的消融研究表明,准确的接触计算和接口上的动态注意力对性能至关重要。我们公开发布了修正后的接口数据集和训练流程,为未来的接口感知装配检索、验证和生成设计模型奠定了基础。

英文摘要:

We present Linkify, a framework for learning from interface-augmented assembly graphs to enable context-aware part retrieval in mechanical assemblies. While recent generative AI methods for CAD have focused largely on isolated parts or monolithic assemblies, the rich geometric information at the interfaces between parts, where function is realized, remains underexplored. We address this gap by recomputing high-fidelity interface geometry for the Fusion 360 Gallery Assembly dataset, correcting missing and erroneous contacts, and generating point-cloud representations of local contact regions. Using this data, we construct assembly graphs whose nodes encode part geometry and whose edges encode interface geometry via a pretrained point-cloud encoder. On top of this representation, we train a Graph Attention Network based on GATv2 to solve a masked part prediction task: given an assembly with one part held out, the model predicts the class of the missing component from a large vocabulary of geometrically clustered parts, thereby approximating a realistic part-retrieval scenario. Compared to non-graph baselines such as logistic regression and k-nearest neighbors operating on aggregated node features, Linkify achieves higher Top-K accuracy and F1 scores. Ablation studies on graph connectivity, edge attributes, and attention mechanisms demonstrate that accurate contact computation and dynamic attention over interfaces are critical for performance. Our corrected interface dataset and training pipeline, released publicly, provide a foundation for future interface-aware models for assembly retrieval, validation, and generative design.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑