Computer Graphics
TU Braunschweig

Tex2Shape: Detailed Full Human Body Geometry from a Single Image


Tex2Shape: Detailed Full Human Body Geometry from a Single Image

We present a simple yet effective method to infer detailed full human body shape from only a single photograph. Our model can infer full-body shape including face, hair, and clothing including wrinkles at interactive frame-rates. Results feature details even on parts that are occluded in the input image. Our main idea is to turn shape regression into an aligned image-to-image translation problem. The input to our method is a partial texture map of the visible region obtained from off-the-shelf methods. From a partial texture, we estimate detailed normal and vector displacement maps, which can be applied to a low-resolution smooth body model to add detail and clothing. Despite being trained purely with synthetic data, our model generalizes well to real-world photographs. Numerous results demonstrate the versatility and robustness of our method.


Author(s): Thiemo Alldieck, Gerard Pons-Moll, Christian Theobalt, Marcus Magnor
Published: October 2019
Type: Article in conference proceedings
Book: IEEE International Conference on Computer Vision (ICCV) (IEEE)
DOI: 10.1109/ICCV.2019.00238
Presented at: IEEE International Conference on Computer Vision (ICCV) 2019
Project(s): Comprehensive Human Performance Capture from Monocular Video Footage  Immersive Digital Reality 

BibTex PDF Link Suppl. Material Code arXiv 



@inproceedings{alldieck2019tex2shape,
  title = {Tex2Shape: Detailed Full Human Body Geometry from a Single Image},
  author = {Alldieck, Thiemo and Pons-Moll, Gerard and Theobalt, Christian and Magnor, Marcus},
  booktitle = {{IEEE} International Conference on Computer Vision ({ICCV})},
  organization = {{IEEE}},
  doi = {10.1109/{ICCV}.2019.00238},
  pages = {2293--2303},
  month = {Oct},
  year = {2019}
}

Authors