本資料は2021年7月08日に社内共有資料として展開していたものを WEBページ向けにリニューアルした内容になります。




  • Problem to Solve


VIBE approach

  • Pretrained Model

  • Temporal Encoder

  • Motion Discriminator



●Lack of in-the-wild ground-truth 3D
●Previous work combine indoor 3D datasets with videos having
2D ground-truth or pseudo ground-truth keypoint annotations

  • Indoor 3D are limited in the number of subjects, range of motion and image complexity

  • Poor amount of video labeled with ground-truth 2D pose

  • Pseudo-ground-truth 2D labels are not reliable for modeling 3D human motion

※Learning 3D Human Dynamics from Video -


●AMASS dataset for 3D motion capture

■What is VIBE