Header logo is

Monocular Expressive Body Regression through Body-Driven Attention

2020

Conference Paper

ps


To understand how people look, interact, or perform tasks,we need to quickly and accurately capture their 3D body, face, and hands together from an RGB image. Most existing methods focus only on parts of the body. A few recent approaches reconstruct full expressive 3D humans from images using 3D body models that include the face and hands. These methods are optimization-based and thus slow, prone to local optima, and require 2D keypoints as input. We address these limitations by introducing ExPose (EXpressive POse and Shape rEgression), which directly regresses the body, face, and hands, in SMPL-X format, from an RGB image. This is a hard problem due to the high dimensionality of the body and the lack of expressive training data. Additionally, hands and faces are much smaller than the body, occupying very few image pixels. This makes hand and face estimation hard when body images are downscaled for neural networks. We make three main contributions. First, we account for the lack of training data by curating a dataset of SMPL-X fits on in-the-wild images. Second, we observe that body estimation localizes the face and hands reasonably well. We introduce body-driven attention for face and hand regions in the original image to extract higher-resolution crops that are fed to dedicated refinement modules. Third, these modules exploit part-specific knowledge from existing face and hand-only datasets. ExPose estimates expressive 3D humans more accurately than existing optimization methods at a small fraction of the computational cost. Our data, model and code are available for research at https://expose.is.tue.mpg.de.

Author(s): Choutas, Vasileios and Pavlakos, Georgios and Bolkart, Timo and Tzionas, Dimitrios and Black, Michael J.
Book Title: Computer Vision - ECCV 2020
Volume: 10
Pages: 20--40
Year: 2020
Month: August

Series: Lecture Notes in Computer Science, 12355
Editors: Vedaldi, Andrea and Bischof, Horst and Brox, Thomas and Frahm, Jan-Michael
Publisher: Springer

Department(s): Perceiving Systems
Research Project(s): Expressive Body Models
Regressing Humans
Optimizing Human Pose and Shape
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

DOI: 10.1007/978-3-030-58607-2_2
Event Name: 16th European Conference on Computer Vision (ECCV 2020)
Event Place: Glasgow, UK

Address: Cham
ISBN: 978-3-030-58606-5
State: Published
URL: https://expose.is.tue.mpg.de

Links: code
Short video
Long video
arxiv
Video:
Video:
Attachments: pdf
suppl

BibTex

@inproceedings{ExPose:2020,
  title = {Monocular Expressive Body Regression through Body-Driven Attention},
  author = {Choutas, Vasileios and Pavlakos, Georgios and Bolkart, Timo and Tzionas, Dimitrios and Black, Michael J.},
  booktitle = {Computer Vision - ECCV 2020},
  volume = {10},
  pages = {20--40},
  series = {Lecture Notes in Computer Science, 12355},
  editors = {Vedaldi, Andrea and Bischof, Horst and Brox, Thomas and Frahm, Jan-Michael},
  publisher = {Springer},
  address = {Cham},
  month = aug,
  year = {2020},
  doi = {10.1007/978-3-030-58607-2_2},
  url = {https://expose.is.tue.mpg.de},
  month_numeric = {8}
}