This media is not supported in your browser
VIEW IN TELEGRAM
NVIDIA introduces GENMO, a unified generalist model for human motion that seamlessly combines motion estimation and generation within a single framework. GENMO supports conditioning on videos, 2D keypoints, text, music, and 3D keyframes, enabling highly versatile motion understanding and synthesis.
Currently, no official code release is available.
Review:
https://t.ly/Q5T_Y
Paper:
https://lnkd.in/ds36BY49
Project Page:
https://lnkd.in/dAYHhuFU
#NVIDIA #GENMO #HumanMotion #DeepLearning #AI #ComputerVision #MotionGeneration #MachineLearning #MultimodalAI #3DReconstruction
Please open Telegram to view this post
VIEW IN TELEGRAM
👍3