Header logo is

Collaborative Regression of Expressive Bodies using Moderation

2021

Conference Paper

ps


Recovering expressive humans from images is essential for understanding human behavior. Methods that estimate 3D bodies, faces, or hands have progressed significantly, yet separately. Face methods recover accurate 3D shape and geometric details, but need a tight crop and struggle with extreme views and low resolution. Whole-body methods are robust to a wide range of poses and resolutions, but provide only a rough 3D face shape without details like wrinkles. To get the best of both worlds, we introduce PIXIE, which produces animatable, whole-body 3D avatars with realistic facial detail, from a single image. For this, PIXIE uses two key observations. First, existing work combines independent estimates from body, face, and hand experts, by trusting them equally. PIXIE introduces a novel moderator that merges the features of the experts, weighted by their confidence. All part experts can contribute to the whole, using SMPL-X’s shared shape space across all body parts. Second, human shape is highly correlated with gender, but existing work ignores this. We label training images as male, female, or non-binary, and train PIXIE to infer “gendered” 3D body shapes with a novel shape loss. In addition to 3D body pose and shape parameters, PIXIE estimates expression, illumination, albedo and 3D facial surface displacements. Quantitative and qualitative evaluation shows that PIXIE estimates more accurate whole-body shape and detailed face shape than the state of the art. Models and code are available at https://pixie.is.tue.mpg.de.

Author(s): Yao Feng and Vasileios Choutas and Timo Bolkart and Dimitrios Tzionas and Michael J. Black
Book Title: 2021 International Conference on 3D Vision (3DV 2021)
Pages: 792--804
Year: 2021
Month: December
Publisher: IEEE

Department(s): Perceiving Systems
Research Project(s): Expressive Body Models
Regressing Humans
Bibtex Type: Conference Paper (conference)
Paper Type: Conference

DOI: 10.1109/3DV53792.2021.00088
Event Name: International Conference on 3D Vision (3DV 2021)
Event Place: Virtual

Address: Piscataway, NJ
ISBN: 978-1-6654-2688-6
State: Published

Links: arXiv
project
Attachments: pdf
suppl

BibTex

@conference{PIXIE:3DV:2021,
  title = {Collaborative Regression of Expressive Bodies using Moderation},
  author = {Feng, Yao and Choutas, Vasileios and Bolkart, Timo and Tzionas, Dimitrios and Black, Michael J.},
  booktitle = {2021 International Conference on 3D Vision (3DV 2021)},
  pages = {792--804},
  publisher = {IEEE},
  address = {Piscataway, NJ},
  month = dec,
  year = {2021},
  doi = {10.1109/3DV53792.2021.00088},
  month_numeric = {12}
}