首个工业级3D打印缺陷检测数据集，助力真实场景下缺陷识别
3D-ADAM: A Dataset for 3D Anomaly Detection in Additive Manufacturing
- 构建工业环境采集的14,120份高分辨率3D扫描数据
- 包含27,346个缺陷标注，覆盖12类缺陷和16类设备特征
- 适合作为工业质检模型的基准测试，推动真实场景落地
表面缺陷是制造中导致良率损失的主要原因，但现有异常检测方法因数据集规模小且不具代表性而难以在实际中部署。为此，我们推出3D-ADAM，首个面向增材制造的3D异常检测大规模工业相关数据集，支持RGB+3D表面缺陷检测。该数据集包含14,120个高分辨率扫描，来自217个独特零件，使用四种工业深度传感器采集，涵盖27,346个缺陷标注（12类）及27,346个机器元件特征标注（16类）。数据在真实工业环境中采集，反映实际生产条件，包括零件位置变化、传感器姿态差异、光照变化和部分遮挡。基准测试表明，3D-ADAM比现有数据集更具挑战性。通过与行业伙伴的专家标注验证，确认其工业相关性。3D-ADAM为开发满足制造需求的鲁棒3D异常检测模型奠定了基础。
原文摘要 · Abstract (English)
Surface defects are a primary source of yield loss in manufacturing, yet existing anomaly detection methods often fail in real-world deployment due to limited and unrepresentative datasets. To overcome this, we introduce 3D-ADAM, a 3D Anomaly Detection in Additive Manufacturing dataset, that is the first large-scale, industry-relevant dataset for RGB+3D surface defect detection in additive manufacturing. 3D-ADAM comprises 14,120 high-resolution scans of 217 unique parts, captured with four industrial depth sensors, and includes 27,346 annotated defects across 12 categories along with 27,346 annotations of machine element features in 16 classes. 3D-ADAM is captured in a real industrial environment and as such reflects real production conditions, including variations in part placement, sensor positioning, lighting, and partial occlusion. Benchmarking state-of-the-art models demonstrates that 3D-ADAM presents substantial challenges beyond existing datasets. Validation through expert labelling surveys with industry partners further confirms its industrial relevance. By providing this benchmark, 3D-ADAM establishes a foundation for advancing robust 3D anomaly detection capable of meeting manufacturing demands.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。