识别部件：3D部件分割与命名
Name That Part: 3D Part Segmentation and Naming
AI总结：
ALIGN-Parts提出了一种高效的一次性3D部件分割与命名方法，通过集合对齐任务实现开放词汇匹配，构建统一本体并引入新指标。
摘要：
我们针对语义3D部件分割问题：将物体分解为具有意义名称的部件。尽管存在带有部件注释的数据集，但这些定义在不同数据集中不一致，限制了鲁棒训练。先前的方法产生未标记的分解或检索单个部件而没有完整的形状注释。我们提出了ALIGN-Parts，将部件命名公式化为直接的集合对齐任务。我们的方法将形状分解为部件let——隐含的3D部件表示——通过双侧分配匹配到部件描述。我们结合了3D部件场的几何线索、多视角视觉特征的外观线索以及语言模型生成的 affordance 描述的语义知识。文本对齐损失确保部件let与文本共享嵌入空间，使在足够数据的情况下能够实现理论上开放词汇的匹配设置。我们的高效且新颖的一次性3D部件分割和命名方法在多个下游任务中得到应用，包括作为可扩展的注释引擎。由于我们的模型支持零样本匹配到任意描述，并且在已知类别中具有校准的预测信心，结合人工验证，我们创建了一个统一的本体，对齐PartNet、3DCoMPaT++和Find3D，包含1794个独特的3D部件。我们引入了两种适用于命名3D部件分割任务的新指标。我们还展示了从我们新创建的TexParts数据集中的一些示例。
英文摘要：
We address semantic 3D part segmentation: decomposing objects into parts with meaningful names. While datasets exist with part annotations, their definitions are inconsistent across datasets, limiting robust training. Previous methods produce unlabeled decompositions or retrieve single parts without complete shape annotations. We propose ALIGN-Parts, which formulates part naming as a direct set alignment task. Our method decomposes shapes into partlets - implicit 3D part representations - matched to part descriptions via bipartite assignment. We combine geometric cues from 3D part fields, appearance cues from multi-view vision features, and semantic knowledge from language-model-generated affordance descriptions. Text-alignment loss ensures partlets share embedding space with text, enabling a theoretically open-vocabulary matching setup, given sufficient data. Our efficient and novel, one-shot, 3D part segmentation and naming method finds applications in several downstream tasks, including serving as a scalable annotation engine. As our model supports zero-shot matching to arbitrary descriptions and confidence-calibrated predictions for known categories, with human verification, we create a unified ontology that aligns PartNet, 3DCoMPaT++, and Find3D, consisting of 1,794 unique 3D parts. We introduce two novel metrics appropriate for the named 3D part segmentation task. We also show examples from our newly created TexParts dataset.
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。
