FeatureFox: Sample-Efficient Panoptic Graph Segmentation for Machining Feature Recognition in B-Rep 3D-CAD Models
This work addresses the data hunger and complexity of learning-based automatic feature recognition for CAD/CAM automation, offering a practical solution for industrial applications with limited labeled data.
FeatureFox introduces a sample-efficient panoptic pipeline for machining feature recognition on B-Rep CAD models, achieving PQ > 0.9 with ~250 training parts compared to ~5,000 for the deep baseline AAGNet, while training on the full dataset takes seconds on a GPU.
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.