Data scarcity fundamentally limits the generalization of bimanual dexterous manipulation, as real-world data collection for dexterous hands is expensive and labor-intensive. Human manipulation videos, as a direct carrier of manipulation knowledge, offer significant potential for scaling up robot learning. However, the substantial embodiment gap between human hands and robotic dexterous hands makes direct pretraining from human videos extremely challenging. To bridge this gap and unleash the potential of large-scale human manipulation video data, we propose DexImit, an automated framework that converts monocular human manipulation videos into physically plausible robot data, without any additional information. DexImit employs a four-stage generation pipeline: (1) reconstructing hand-object interactions from arbitrary viewpoints with near-metric scale; (2) performing subtask decomposition and bimanual scheduling; (3) synthesizing robot trajectories consistent with the demonstrated interactions; (4) comprehensive data augmentation for zero-shot real-world deployment. Building on these designs, DexImit can generate large-scale robot data based on human videos, either from the Internet or video generation models. DexImit is capable of handling diverse manipulation tasks, including tool use (e.g., cutting an apple), long-horizon tasks (e.g., making a beverage), and fine-grained manipulations (e.g., stacking cups).

翻译：数据稀缺从根本上限制了双手灵巧操作的泛化能力，因为灵巧手在现实世界中的数据收集成本高昂且劳动密集。人体操作视频作为操作知识的直接载体，为扩展机器人学习提供了巨大潜力。然而，人手与机器人灵巧手之间存在巨大的具身鸿沟，使得直接从人体视频进行预训练极具挑战性。为弥合这一鸿沟并释放大规模人体操作视频数据的潜力，我们提出了DexImit，一个无需任何额外信息即可将单目人体操作视频转换为物理上合理的机器人数据的自动化框架。DexImit采用四阶段生成流程：（1）从任意视角以近度量尺度重建手-物交互；（2）执行子任务分解与双手调度；（3）合成与演示交互一致的机器人轨迹；（4）为零样本现实世界部署进行全面的数据增强。基于这些设计，DexImit能够基于来自互联网或视频生成模型的人体视频生成大规模机器人数据。DexImit能够处理多样化的操作任务，包括工具使用（例如切苹果）、长时程任务（例如制作饮料）以及精细操作（例如叠杯子）。