AI RESEARCH
SFHand: Learning Embodied Manipulation by Streaming Egocentric 3D Hand Forecasting
arXiv CS.CV
•
ArXi:2511.18127v2 Announce Type: replace Real-time 3D hand forecasting is a critical component for fluid human-computer interaction in applications like AR and assistive robotics. However, existing methods are ill-suited for these scenarios, as they typically require offline access to accumulated video sequences and cannot incorporate language guidance that conveys task intent. To overcome these limitations, we