MotioNet: 3D Human Motion Reconstruction from Monocular Video with Skeleton Consistency
Technical Papers Fast Forward Presenter Event Type
Technical Papers Q&A
TimeSaturday, 12 December 202011:25 - 11:30 SGT
LocationZoom Room 7
DescriptionMotioNet is a deep neural network that reconstructs a kinematic skeleton from monocular video, and directly outputs the complete, commonly used, motion representation in character animation.
Technical Papers Fast Forward Presenter