Automatic feature recognition (AFR) on B-Rep 3D-CAD models is central to CAD/CAM automation, yet most learning-based methods are complex, data-hungry, and evaluate instance grouping and semantic labeling separately. We present FeatureFox, a panoptic AFR pipeline that outputs machining instances with semantic labels: a calibrated binary edge classifier on enriched edge attributes localizes feature boundaries, instances are recovered as connected components in a pruned face-adjacency graph, and a per-instance classifier predicts the machining class from aggregated subgraph attributes. We evaluate on MFInstSeg using Panoptic Quality (PQ), which jointly scores instance separation and semantic correctness. FeatureFox is substantially more sample- and compute-efficient than the deep baseline AAGNet, reaching $\mathrm{PQ}>0.9$ with $\sim250$ training parts versus $\sim5{,}000$ for AAGNet, and training on the full MFInstSeg set takes seconds on a GPU. On the full training set, AAGNet surpasses FeatureFox marginally in PQ, while FeatureFox remains slightly ahead in feature-level recognition and localization accuracy. Finally, leveraging its low data requirement, we train FeatureFox on $270$ manually labeled industrial CAD parts and show qualitative generalization to an unseen real industrial part, indicating practical real-world applicability.

翻译：在B-Rep三维CAD模型上的自动特征识别（AFR）是CAD/CAM自动化的核心，然而大多数基于学习的方法复杂、数据需求量大，且分别评估实例分组与语义标注。我们提出FeatureFox——一种全景AFR流水线，可输出带语义标签的加工实例：基于增强边属性的校准二元边分类器定位特征边界，通过修剪后的面邻接图中的连通分量恢复实例，并由逐实例分类器根据聚合的子图属性预测加工类别。我们使用全景质量（PQ）在MFInstSeg数据集上进行评估，该指标联合评分实例分割与语义正确性。FeatureFox在样本与计算效率上显著优于深度基线模型AAGNet，仅需约250个训练零件即可达到PQ>0.9，而AAGNet需约5000个零件；且基于完整MFInstSeg训练集的GPU训练仅需数秒。在完整训练集上，AAGNet在PQ上略超FeatureFox，而FeatureFox在特征级识别与定位精度上仍稍占优势。最后，利用其低数据需求，我们使用270个手动标注的工业CAD零件训练FeatureFox，并展示了其对未见真实工业零件的定性泛化能力，表明其具备实际工业应用潜力。