ObjectTwin：测量以捕获为锚的数字孪生资产对应差距
原标题：ObjectTwin: Measuring the Asset Correspondence Gap for Capture-Anchored Digital Twins
AI 摘要
论文提出 ObjectTwin，一种以扫描为基准的测量协议：固定实例、相机、扫描投影支撑、记录深度、度量锚点和评估分母，仅替换物体表示，从而量化生成资产替换观测实例后与校准观测的一致性损失（资产对应差距）。在两个室内 RGB-D 采集域和两个生成后端上，可见且锚定的生成资产 MaskIoU 下降 0.302–0.497，所有场景级估计均为正，且同一输入下生成器偏好随采集域反转。研究将采集对应性确立为生成资产质量与更强物理或任务级评估之间可单独测量的接口。
正文节选
ObjectTwin: Measuring the Asset Correspondence Gap for Capture-Anchored Digital Twins Abstract Object-wise reconstruction increasingly inserts generated meshes into captured scenes as editable proxies for observed objects. This use creates a requirement absent from isolated-asset scores and pose estimates: at the captured metric state, the proxy should reproduce calibrated observations of the same instance. We present ObjectTwin, a scan-grounded measurement protocol that freezes the instance, ca