Event Cameras for Melt-Pool Monitoring in Additive Manufacturing: A Benchmark and a Cross-Machine Transfer Analysis
Computer Science > Computer Vision and Pattern Recognition arXiv:2610.06973 (cs) [Submitted on 3 Oct 2026] Title: Event Cameras for Melt-Pool Monitoring in Additive Manufacturing: A Benchmark and a Cross-Machine Transfer Analysis Authors: Mohamad Yazan Sadoun, Sarah Sharif, Yingtao Liu, Zahed Siddique, Yaser Mike Banad.
计算机科学 > 计算机视觉与模式识别 arXiv:2610.06973 (cs) [提交于 2026 年 10 月 3 日] 标题：用于增材制造熔池监测的事件相机：基准测试与跨机器迁移分析 作者：Mohamad Yazan Sadoun, Sarah Sharif, Yingtao Liu, Zahed Siddique, Yaser Mike Banad。
Abstract: Melt-pool monitoring is central to qualifying metal additive manufacturing (AM), yet no public event-camera benchmark exists for this domain. Event cameras report per-pixel brightness changes with microsecond timing instead of reading full frames, giving the temporal resolution AM transients demand at a fraction of the data rate.
摘要：熔池监测对于金属增材制造（AM）的质量鉴定至关重要，但目前该领域尚无公开的事件相机基准测试。事件相机通过微秒级的时间精度报告每个像素的亮度变化，而非读取完整帧，这以极低的数据速率提供了增材制造瞬态过程所需的时间分辨率。
We present SynAM-E (Synthetic AM Events), the first public multi-source simulated event-camera benchmark for metal-AM melt-pool monitoring: 85 physics-calibrated event shards from 15 sources across 8 institutions, with public baselines and fixed cross-machine evaluation splits.
我们提出了 SynAM-E（合成增材制造事件），这是首个用于金属增材制造熔池监测的公开多源模拟事件相机基准测试：包含来自 8 个机构 15 个来源的 85 个物理校准事件片段，并提供公开基准和固定的跨机器评估划分。
On a single-machine case study, event-spatial monitoring matches dense-frame accuracy (0.874 versus 0.863 macro-F1), and the absolute intensity that events discard adds only +0.006 under fusion. On the NIST Additive Manufacturing Metrology Testbed (AMMT) build, a near-sensor event-rate counter recovers a raw-frame-confirmed 528.7 Hz intensity oscillation at ~380 times less sensor readout than the frame stream requires.
在单机案例研究中，事件空间监测的准确性与密集帧相当（宏 F1 分数为 0.874 对比 0.863），且事件丢弃的绝对强度在融合后仅增加 +0.006。在 NIST 增材制造计量测试台（AMMT）构建中，近传感器事件率计数器恢复了经原始帧确认的 528.7 Hz 强度振荡，其传感器读取量比帧流需求减少了约 380 倍。
A compact 93 k-parameter spiking model runs at 15 times lower modeled inference energy for a 0.073 macro-F1 cost. Every cross-source task includes a built-in trust test against camera identity shortcuts: process-type classification passes while material classification remains confounded by camera band, a corpus-structural limitation the release documents and the trust test exposes.
一个紧凑的 93k 参数脉冲模型在推理能耗降低 15 倍的情况下，仅付出了 0.073 的宏 F1 分数代价。每项跨源任务都包含一个针对相机身份捷径的内置信任测试：工艺类型分类通过了测试，而材料分类仍受相机波段的干扰，这是该发布文档所记录且信任测试所揭示的一种语料库结构性局限。