部件识别与命名：三维零件分割及标注系统

Name That Part: 3D Part Segmentation and Naming

December 19, 2025

作者: Soumava Paul, Prakhar Kaushik, Ankit Vaidya, Anand Bhattad, Alan Yuille

cs.AI

摘要

我們致力於解決語義3D部件分割問題：將物體分解為具有意義名稱的部件。現有數據集雖包含部件標註，但其定義標準不一，限制了模型的魯棒性訓練。先前方法僅能生成未標記的分解結果或檢索單個部件，且缺乏完整形狀標註。我們提出ALIGN-Parts方法，將部件命名建模為直接的集合對齊任務。該方法通過二分圖匹配，將形體分解為隱式3D部件表徵的「部件元」，並與部件描述進行匹配。我們融合了三類特徵：來自3D部件場的幾何線索、多視角視覺特徵的外觀信息，以及語言模型生成的功能性描述所承載的語義知識。文本對齊損失確保部件元與文本共享嵌入空間，在數據充足條件下實現理論上的開放詞彙匹配框架。我們這種高效新穎的單次3D部件分割與命名方法，可應用於多種下游任務，包括作為可擴展的自動標註引擎。由於模型支持對任意描述的零樣本匹配，並能對已知類別生成置信度校準的預測，經人工驗證後，我們構建了統一的本體框架，整合了PartNet、3DCoMPaT++和Find3D數據集，包含1,794個獨特3D部件。同時展示了新構建的Tex-Parts數據集樣例，並針對命名3D部件分割任務提出了兩種創新評估指標。

English

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 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 also show examples from our newly created Tex-Parts dataset. We also introduce 2 novel metrics appropriate for the named 3D part segmentation task.