AMVOS: Additive Manufacturing Video Object Segmentation Dataset
收藏DataCite Commons2026-05-15 更新2026-05-18 收录
下载链接：
https://dataverse.harvard.edu/citation?persistentId=doi:10.7910/DVN/5GSQTS
下载链接
链接失效反馈官方服务：
资源简介：
<p>This dataset provides labeled video frames from four additive manufacturing (AM) processes for video object segmentation (VOS) tasks. It contains 90 video segments comprising 900 individually annotated frames across five AM datasets: laser hot-wire directed energy deposition (LHW-DED), tungsten inert gas wire arc additive manufacturing (TIG-WAAM), plasma arc welding (PAW), visible-light polymer extrusion (visPolymer), and near-infrared polymer extrusion (irPolymer).</p>
<p>Each video segment consists of 10 contiguous frames with corresponding pixel-level object instance annotations. Depending on the process, two of four object classes are labeled per frame: <b>Melt Pool</b>, <b>Feed Wire</b>, <b>Nozzle</b>, or <b>Material</b>. Raw frames are provided as .jpg files and annotations as palettized .png files.</p>
<p>The dataset follows the directory structure of established VOS benchmarks (DAVIS, YouTube-VOS, MOSE), enabling direct integration into VOS model training and evaluation pipelines for foundation model fine-tuning, domain adaptation, or zero-shot performance benchmarking. Data was collected at Oak Ridge National Laboratory's Manufacturing Demonstration Facility.</p>
提供机构：
Harvard Dataverse
创建时间：
2026-05-14
