VIBE:動画からの人体の姿勢・形状推定


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。



■Contents

 

Introduction

  • Problem to Solve


Dataset


VIBE approach

  • Pretrained Model

  • Temporal Encoder

  • Motion Discriminator


Results



■Problem

 
●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 -

https://arxiv.org/pdf/1812.01601.pdf



■Dataset

 
●AMASS dataset for 3D motion capture


■What is VIBE