On November 10, the physical AI physical data company Nuoyiteng Robotics announced today that it will publicly release the high-precision hand motion capture data set HipHi-hand on the Hugging Face platform. This data set has been used to train NVIDIA EgoHand, a 3D hand reconstruction model built on the NVIDIA Isaac Capture unified framework. The model only requires first-person view video captured by a monocular camera to accurately restore the three-dimensional posture of the hand.

Disclaimer:Webull uses external vendor Google Translation Service for news translations where we endeavour to ensure these are correct, however, we recommend that you please double-check this information accordingly. Webull is not responsible for translation errors or issues.