نسخة أولية وصول مفتوح
OmniHOI: Dexterous Hand-Object Interaction from Monocular Human Video
Monocular videos of human manipulation provide abundant dexterous demonstrations, yet reconstructing hand-object interaction from a single view and transferring it to robot hands remain difficult, limiting their direct use for robot execution. Prior methods either require task-specific RL training, limiting scalability …