Perceiving Systems, Computer Vision

VIBE: Video Inference for Human Body Pose and Shape Estimation

2020

Conference Paper

ps


Human motion is fundamental to understanding behavior. Despite progress on single-image 3D pose and shape estimation, existing video-based state-of-the-art methodsfail to produce accurate and natural motion sequences due to a lack of ground-truth 3D motion data for training. To address this problem, we propose “Video Inference for Body Pose and Shape Estimation” (VIBE), which makes use of an existing large-scale motion capture dataset (AMASS) together with unpaired, in-the-wild, 2D keypoint annotations. Our key novelty is an adversarial learning framework that leverages AMASS to discriminate between real human motions and those produced by our temporal pose and shape regression networks. We define a temporal network architecture and show that adversarial training, at the sequence level, produces kinematically plausible motion sequences without in-the-wild ground-truth 3D labels. We perform extensive experimentation to analyze the importance of motion and demonstrate the effectiveness of VIBE on challenging 3D pose estimation datasets, achieving state-of-the-art performance. Code and pretrained models are available at https://github.com/mkocabas/VIBE

Author(s): Muhammed Kocabas and Nikos Athanasiou and Michael J. Black
Book Title: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020)
Pages: 5252--5262
Year: 2020
Month: June
Publisher: IEEE

Department(s): Perceiving Systems
Research Project(s): Regressing Humans
Humans from Video
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

DOI: 10.1109/CVPR42600.2020.00530
Event Name: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020)
Event Place: Seattle, WA, USA

Address: Piscataway, NJ
ISBN: 978-1-7281-7168-5
State: Published

Links: arXiv
code
video
supplemental video
pdf
Video:
Video:

BibTex

@inproceedings{VIBE:CVPR:2020,
  title = {{VIBE}: Video Inference for Human Body Pose and Shape Estimation},
  author = {Kocabas, Muhammed and Athanasiou, Nikos and Black, Michael J.},
  booktitle = {2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020)},
  pages = {5252--5262},
  publisher = {IEEE},
  address = {Piscataway, NJ},
  month = jun,
  year = {2020},
  doi = {10.1109/CVPR42600.2020.00530},
  month_numeric = {6}
}